==================================================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_004/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 16 items test_swiglu_dyn_quant_v2.py [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:37:32.756.164 [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 = 0.952794, [21] [bootstrap]: 0.00064626 [type_inference]: 0.812827 [event_method]: 4.72e-05 [auto_monad]: 0.0002745 [graph_reusing]: 7.31999e-06 [inline]: 4.76002e-06 [add_attr]: 0.0767374, [1] [add_attr_with_inline]: 0.0767211, [1] [Cycle 1]: 0.00014503, [2] [tag_attr]: 4.236e-05 [meta_addattr_fg_expand]: 8.73001e-06 [parallel-infer-symbol]: 3.95998e-06 [pre_auto_parallel]: 7.353e-05 [insert-virtual-dataset]: 3.09999e-06 [parallel-infer-symbol-second]: 9.00007e-07 [dataset_repeat_opt]: 2.32001e-06 [pipeline_split]: 1.95001e-06 [optimize]: 0.0608723, [53] [py_interpret_to_execute]: 5.04e-05 [rewriter_before_opt_a]: 0.00016523 [opt_a]: 0.011486, [2] [Cycle 1]: 0.00921221, [45] [expand_dump_flag]: 4.02002e-06 [switch_simplify]: 5.961e-05 [loop_unroll]: 4.432e-05 [a_1]: 0.00143686 [with_stream_mark]: 3.721e-05 [recompute_prepare]: 2.793e-05 [updatestate_depend_eliminate]: 1.35e-05 [updatestate_assign_eliminate]: 9.77001e-06 [updatestate_loads_eliminate]: 1.04e-05 [parameter_eliminate]: 2.73998e-06 [a_2]: 0.00033219 [accelerated_algorithm]: 4.955e-05 [shard]: 2.64001e-06 [meta_shard_fg_expand]: 7.81001e-06 [shard_inline]: 2.208e-05 [merge_send_recv]: 3.868e-05 [auto_parallel]: 1.931e-05 [parallel]: 4.292e-05 [flash_sp]: 2.613e-05 [merge_comm]: 1.328e-05 [allreduce_fusion]: 1.167e-05 [matmul_add_comm_reduction]: 2.201e-05 [allreduce_slice_to_reducescatter]: 8.50006e-07 [virtual_shard_identity]: 2.589e-05 [virtual_dataset]: 2.062e-05 [get_grad_eliminate_]: 2.087e-05 [virtual_output]: 2.006e-05 [merge_forward]: 1.245e-05 [cell_reuse_recompute_pass]: 2.14e-06 [offload_activation]: 2.284e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.258e-05 [merge_recompute_call_nodes]: 1.83997e-06 [before_grad]: 3.719e-05 [set_forward_comm_id_for_comm_node_pass]: 1.395e-05 [meta_fg_expand]: 1.038e-05 [flash_sp_send_recv_attached]: 5.37999e-06 [receive_attached]: 1.264e-05 [after_resolve]: 2.696e-05 [a_after_grad]: 0.00010818 [renormalize]: 0.00572805 [add_forward_monad_depend]: 1.854e-05 [auto_monad_grad]: 2.42001e-06 [auto_monad_eliminator]: 4.56e-05 [cse]: 0.00027204 [a_3]: 0.00016633 [Cycle 2]: 0.00225645, [45] [expand_dump_flag]: 2.41998e-06 [switch_simplify]: 2.251e-05 [loop_unroll]: 2.063e-05 [a_1]: 0.00065056 [with_stream_mark]: 3.111e-05 [recompute_prepare]: 2.349e-05 [updatestate_depend_eliminate]: 1.288e-05 [updatestate_assign_eliminate]: 1.093e-05 [updatestate_loads_eliminate]: 9.61e-06 [parameter_eliminate]: 2.79001e-06 [a_2]: 0.0003035 [accelerated_algorithm]: 3.199e-05 [shard]: 2.91e-06 [meta_shard_fg_expand]: 8.28001e-06 [shard_inline]: 1.972e-05 [merge_send_recv]: 2.042e-05 [auto_parallel]: 1.957e-05 [parallel]: 1.061e-05 [flash_sp]: 4.72e-06 [merge_comm]: 1.301e-05 [allreduce_fusion]: 1.252e-05 [matmul_add_comm_reduction]: 2.506e-05 [allreduce_slice_to_reducescatter]: 1.15001e-06 [virtual_shard_identity]: 3.269e-05 [virtual_dataset]: 2.372e-05 [get_grad_eliminate_]: 2.563e-05 [virtual_output]: 2.474e-05 [merge_forward]: 3.353e-05 [cell_reuse_recompute_pass]: 4.18001e-06 [offload_activation]: 2.618e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.976e-05 [merge_recompute_call_nodes]: 1.74e-06 [before_grad]: 4.742e-05 [set_forward_comm_id_for_comm_node_pass]: 1.542e-05 [meta_fg_expand]: 1.104e-05 [flash_sp_send_recv_attached]: 2.88998e-06 [receive_attached]: 2.53e-06 [after_resolve]: 3.352e-05 [a_after_grad]: 3.803e-05 [renormalize]: 2.29978e-07 [add_forward_monad_depend]: 5.67001e-06 [auto_monad_grad]: 3.31001e-06 [auto_monad_eliminator]: 4.12e-05 [cse]: 9.419e-05 [a_3]: 0.00014938 [py_interpret_to_execute_after_opt_a]: 3.535e-05 [slice_cell_reuse_recomputed_activation]: 3.34001e-06 [rewriter_after_opt_a]: 0.0005417 [convert_after_rewriter]: 2.671e-05 [order_py_execute_after_rewriter]: 1.679e-05 [mutable_eliminate]: 0.00088902 [opt_b]: 0.00089068, [1] [Cycle 1]: 0.00087864, [7] [b_1]: 0.00061829 [b_2]: 3.17e-05 [updatestate_depend_eliminate]: 2.377e-05 [updatestate_assign_eliminate]: 1.536e-05 [updatestate_loads_eliminate]: 1.326e-05 [renormalize]: 1.17e-06 [cse]: 0.00011706 [optimize_parallel_all_gather_comm]: 4.803e-05 [overlap_param_gather]: 2.41e-06 [cconv]: 4.667e-05 [loop_unroll]: 0.0448482 [opt_after_cconv]: 0.00037038, [1] [Cycle 1]: 0.00035636, [7] [c_1]: 0.00013253 [parameter_eliminate]: 7.16001e-06 [updatestate_depend_eliminate]: 2.471e-05 [updatestate_assign_eliminate]: 1.106e-05 [updatestate_loads_eliminate]: 1.025e-05 [cse]: 0.00011905 [renormalize]: 1.14e-06 [remove_dup_value]: 0.00010783 [tuple_transform]: 0.00028943, [1] [Cycle 1]: 0.00028245, [4] [d_1]: 0.00023433 [none_parameter_eliminate]: 2.64001e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 2.152e-05 [partial_unused_args_eliminate]: 2.51e-06 [add_recomputation]: 0.00015843 [cse_after_recomputation]: 7.689e-05, [1] [Cycle 1]: 7.049e-05, [1] [cse]: 6.162e-05 [environ_conv]: 3.74e-05 [swap_dp_allreduce_reducescatter]: 1.804e-05 [bias_add_comm_swap]: 3.46999e-06 [label_micro_interleaved_index]: 7.13998e-06 [label_fine_grained_interleaved_index]: 2.71999e-06 [merge_cast_opt]: 1.44e-06 [slice_recompute_activation]: 2.31e-06 [micro_interleaved_order_control]: 2.56998e-06 [assign_add_opt]: 1.76998e-06 [ForceFp32Comm]: 1.14998e-06 [remove_cast_before_assign_add]: 1.44e-06 [full_micro_interleaved_order_control]: 2.11e-06 [reorder_send_recv_between_fp_bp]: 3.23998e-06 [comm_op_add_attrs]: 1.08001e-06 [add_comm_op_reuse_tag]: 9.70002e-07 [interleave_split_concat_branches]: 1.17999e-06 [interleave_parallel_branches]: 1.04998e-06 [overlap_opt_shard_in_pipeline]: 2.646e-05 [overlap_opt_shard_grad_in_pipeline]: 1.74e-06 [control_data_broadcast_order]: 3.862e-05 [grouped_pairwise_exchange_alltoall]: 1.58002e-06 [offloading_packed_experts]: 1.093e-05 [overlap_recompute_and_grad_model_parallel]: 1.061e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.17e-06 [overlap_recompute_allgather_and_fa_grad]: 1.57001e-06 [overlap_recompute_comm]: 2.17001e-06 [overlap_grad_ring_attention]: 9.81998e-06 [overlap_grad_flash_sp]: 6.643e-05 [begin_end_overlap_inline]: 5.59987e-07 [split_matmul_comm_elemetwise]: 2.81999e-06 [split_layernorm_comm]: 2.09e-06 [handle_group_info]: 1.42e-06 [symbol_engine_optimizer]: 0.00020879, [1] [Cycle 1]: 0.0002015, [6] [build]: 1.731e-05 [elim_shapecalc]: 3.753e-05 [elim_not_effective]: 4.347e-05 [opt_reshape]: 2.813e-05 [fold_const_symbol]: 3.297e-05 [renormalize]: 3.50003e-07 [detach_backward]: 3.58e-06 [pipeline_parallel_scheduler]: 1.72001e-06 [auto_monad_reorder]: 5.558e-05 [get_jit_bprop_graph]: 2.37999e-06 [rewriter_after_jit_bprop_graph]: 7.77e-06 [opt_after_jit_grad]: 0.00088743 [validate]: 0.00013425 Sums bootstrap : 0.000646s : 0.07% type_inference : 0.812827s : 92.93% event_method : 0.000047s : 0.01% auto_monad : 0.000274s : 0.03% graph_reusing : 0.000007s : 0.00% inline : 0.000005s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000042s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000009s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000074s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000050s : 0.01% optimize.rewriter_before_opt_a : 0.000165s : 0.02% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000082s : 0.01% optimize.opt_a.loop_unroll : 0.000065s : 0.01% optimize.opt_a.a_1 : 0.002087s : 0.24% optimize.opt_a.with_stream_mark : 0.000068s : 0.01% optimize.opt_a.recompute_prepare : 0.000051s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000026s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000020s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000636s : 0.07% optimize.opt_a.accelerated_algorithm : 0.000082s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000016s : 0.00% optimize.opt_a.shard_inline : 0.000042s : 0.00% optimize.opt_a.merge_send_recv : 0.000059s : 0.01% optimize.opt_a.auto_parallel : 0.000039s : 0.00% optimize.opt_a.parallel : 0.000054s : 0.01% optimize.opt_a.flash_sp : 0.000031s : 0.00% optimize.opt_a.merge_comm : 0.000026s : 0.00% optimize.opt_a.allreduce_fusion : 0.000024s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000047s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000059s : 0.01% optimize.opt_a.virtual_dataset : 0.000044s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000046s : 0.01% optimize.opt_a.virtual_output : 0.000045s : 0.01% optimize.opt_a.merge_forward : 0.000046s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000049s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000092s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000085s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000029s : 0.00% optimize.opt_a.meta_fg_expand : 0.000021s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000015s : 0.00% optimize.opt_a.after_resolve : 0.000060s : 0.01% optimize.opt_a.a_after_grad : 0.000146s : 0.02% optimize.opt_a.renormalize : 0.005728s : 0.65% optimize.opt_a.add_forward_monad_depend : 0.000024s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000087s : 0.01% optimize.opt_a.cse : 0.000366s : 0.04% optimize.opt_a.a_3 : 0.000316s : 0.04% optimize.py_interpret_to_execute_after_opt_a : 0.000035s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000542s : 0.06% optimize.convert_after_rewriter : 0.000027s : 0.00% optimize.order_py_execute_after_rewriter : 0.000017s : 0.00% optimize.mutable_eliminate : 0.000889s : 0.10% optimize.opt_b.b_1 : 0.000618s : 0.07% optimize.opt_b.b_2 : 0.000032s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000117s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000048s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000047s : 0.01% optimize.loop_unroll : 0.044848s : 5.13% optimize.opt_after_cconv.c_1 : 0.000133s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000025s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.cse : 0.000119s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000108s : 0.01% optimize.tuple_transform.d_1 : 0.000234s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000022s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000158s : 0.02% optimize.cse_after_recomputation.cse : 0.000062s : 0.01% optimize.environ_conv : 0.000037s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000018s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000026s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000039s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000011s : 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 : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000066s : 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 : 0.000017s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000038s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000043s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000028s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000033s : 0.00% 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 : 0.000056s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000887s : 0.10% validate : 0.000134s : 0.02% Time group info: ------[substitution.] 0.000782 231 6.12% : 0.000048s : 6: substitution.arithmetic_simplify 0.73% : 0.000006s : 13: substitution.elim_not_effective 2.15% : 0.000017s : 12: substitution.float_tuple_getitem_switch 0.62% : 0.000005s : 13: substitution.fold_const_symbol 2.22% : 0.000017s : 17: substitution.graph_param_transform 41.34% : 0.000323s : 7: substitution.inline 1.90% : 0.000015s : 26: substitution.j_node_and_user_rematch 3.00% : 0.000023s : 2: substitution.less_batch_normalization 2.16% : 0.000017s : 8: substitution.minmaximum_grad 0.34% : 0.000003s : 3: substitution.opt_reshape 2.43% : 0.000019s : 26: substitution.remove_not_recompute_node 0.82% : 0.000006s : 2: substitution.replace_old_param 6.30% : 0.000049s : 8: substitution.reshape_eliminate 6.97% : 0.000055s : 16: substitution.tuple_list_convert_item_index_to_positive 3.20% : 0.000025s : 16: substitution.tuple_list_get_item_const_eliminator 4.66% : 0.000036s : 16: substitution.tuple_list_get_item_depend_reorder 10.50% : 0.000082s : 24: substitution.tuple_list_get_item_eliminator 4.54% : 0.000036s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 0.812699 2 99.51% : 0.808730s : 1: type_inference.infer 0.49% : 0.003969s : 1: type_inference.specialize ------[replace.] 0.000074 7 100.00% : 0.000074s : 7: replace.inline ------[match.] 0.000319 7 100.00% : 0.000319s : 7: match.inline ------[predicate.] 0.000697 4346 0.83% : 0.000006s : 42: predicate.accumulaten_eliminater 0.87% : 0.000006s : 17: predicate.ad_related_special_op_eliminate 0.69% : 0.000005s : 35: predicate.addn_check_dump 0.82% : 0.000006s : 42: predicate.addn_zero_filter 0.79% : 0.000005s : 42: predicate.adjust_all_reduce_mul_add 2.08% : 0.000015s : 77: predicate.arithmetic_simplify 0.82% : 0.000006s : 42: predicate.cast_eliminate 0.77% : 0.000005s : 34: predicate.check_bprop_eliminate 0.73% : 0.000005s : 35: predicate.compare_switch_simplify 0.22% : 0.000002s : 17: predicate.const_output_eliminate 0.67% : 0.000005s : 35: predicate.depend_value_elim 0.82% : 0.000006s : 42: predicate.dict_get_item_const_eliminator 0.92% : 0.000006s : 42: predicate.dict_get_item_eliminator 0.79% : 0.000006s : 42: predicate.dict_set_item_eliminator 1.20% : 0.000008s : 34: predicate.dumpgradient_eliminate 0.24% : 0.000002s : 17: predicate.elim_not_effective 0.44% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.18% : 0.000008s : 59: predicate.environ_add_const_eliminate 1.20% : 0.000008s : 59: predicate.environ_get_add_eliminate 1.16% : 0.000008s : 59: predicate.environ_get_depend_swap 2.00% : 0.000014s : 94: predicate.environ_get_eliminate 1.16% : 0.000008s : 59: predicate.environ_get_set_eliminate 0.96% : 0.000007s : 49: predicate.exchange_switch_depend_value 1.32% : 0.000009s : 49: predicate.float_depend_g_call 0.72% : 0.000005s : 35: predicate.float_environ_get_switch 1.22% : 0.000009s : 52: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 17: predicate.fold_const_symbol 0.93% : 0.000006s : 35: predicate.get_grad_eliminate 0.24% : 0.000002s : 17: predicate.graph_param_transform 0.74% : 0.000005s : 35: predicate.incorporate_call 0.63% : 0.000004s : 35: predicate.incorporate_call_switch 5.64% : 0.000039s : 195: predicate.inline 1.16% : 0.000008s : 35: predicate.inline_without_move 0.41% : 0.000003s : 35: predicate.j_node_and_user_rematch 1.46% : 0.000010s : 35: predicate.less_batch_normalization 1.73% : 0.000012s : 76: predicate.list_to_tuple_eliminator_ 2.26% : 0.000016s : 118: predicate.load_eliminater 2.40% : 0.000017s : 17: predicate.loop_unroll_after_grad 1.33% : 0.000009s : 63: predicate.loop_unroll_before_grad 1.86% : 0.000013s : 76: predicate.make_slice_get_slice_eliminator 0.73% : 0.000005s : 35: predicate.merge_addn 0.70% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.77% : 0.000005s : 34: predicate.mini_step_allgather_replace 0.85% : 0.000006s : 42: predicate.minmaximum_grad 1.10% : 0.000008s : 17: predicate.mutable_eliminate 0.44% : 0.000003s : 17: predicate.opt_reshape 0.49% : 0.000003s : 17: predicate.parallel_virtual_node 1.29% : 0.000009s : 49: predicate.partial_defer_inline 1.23% : 0.000009s : 59: predicate.partial_eliminate 0.78% : 0.000005s : 42: predicate.print_const_string_wrapper 0.71% : 0.000005s : 35: predicate.reduce_all_const_elim 1.06% : 0.000007s : 42: predicate.reduce_eliminate 2.38% : 0.000017s : 118: predicate.redundant_stop_gradient_eliminater 0.45% : 0.000003s : 35: predicate.remove_not_recompute_node 1.17% : 0.000008s : 76: predicate.replace_applicator 0.55% : 0.000004s : 35: predicate.replace_old_param 0.29% : 0.000002s : 17: predicate.reset_defer_inline 0.98% : 0.000007s : 42: predicate.reshape_eliminate 0.76% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.47% : 0.000003s : 17: predicate.row_tensor_eliminate 0.94% : 0.000007s : 34: predicate.same_eliminate 0.43% : 0.000003s : 35: predicate.set_cell_output_no_recompute 0.99% : 0.000007s : 35: predicate.shard_identity_eliminate 0.80% : 0.000006s : 34: predicate.special_op_eliminate 0.83% : 0.000006s : 35: predicate.specialize_transform 1.05% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 1.03% : 0.000007s : 35: predicate.stack_unstack_eliminate 0.39% : 0.000003s : 17: predicate.switch_call_monad_eliminater 1.02% : 0.000007s : 49: predicate.switch_defer_inline 1.72% : 0.000012s : 83: predicate.switch_layer_defer_inline 3.44% : 0.000024s : 164: predicate.switch_simplify 0.80% : 0.000006s : 42: predicate.tile_eliminate 0.78% : 0.000005s : 42: predicate.transpose_eliminate 1.77% : 0.000012s : 76: predicate.tuple_list_convert_item_index_to_positive 1.87% : 0.000013s : 76: predicate.tuple_list_get_item_const_eliminator 1.75% : 0.000012s : 76: predicate.tuple_list_get_item_depend_reorder 3.17% : 0.000022s : 111: predicate.tuple_list_get_item_eliminator 1.70% : 0.000012s : 76: predicate.tuple_list_get_set_item_eliminator 2.60% : 0.000018s : 111: predicate.tuple_list_set_item_eliminator 1.61% : 0.000011s : 76: predicate.tuple_to_list_eliminator_ 2.21% : 0.000015s : 118: predicate.updatestate_pure_node_eliminater 3.12% : 0.000022s : 153: predicate.updatestate_useless_node_eliminater 0.50% : 0.000003s : 17: predicate.value_based_eliminate 0.78% : 0.000005s : 35: predicate.virtual_dataset_eliminate 0.88% : 0.000006s : 35: predicate.virtual_output_eliminate 0.37% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.60% : 0.000004s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.007666 54 77.20% : 0.005918s : 45: func_graph_cloner_run.FuncGraphClonerGraph 22.80% : 0.001747s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.145023 192 0.00% : 0.000004s : 1: ForceFp32Comm 6.70% : 0.076744s : 1: add_attr 6.70% : 0.076726s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000166s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000285s : 1: auto_monad 0.01% : 0.000062s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.06% : 0.000670s : 1: bootstrap 0.00% : 0.000053s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000043s : 1: control_data_broadcast_order 0.00% : 0.000035s : 1: convert_after_rewriter 0.01% : 0.000081s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000043s : 1: environ_conv 0.00% : 0.000056s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000008s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 3.92% : 0.044872s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.08% : 0.000907s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 3.85% : 0.044114s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000048s : 1: opt.transform.mutable_eliminate 0.33% : 0.003802s : 78: opt.transform.opt_a 0.01% : 0.000127s : 1: opt.transform.opt_after_cconv 0.01% : 0.000083s : 1: opt.transform.opt_after_jit_grad 0.05% : 0.000607s : 28: opt.transform.opt_b 0.02% : 0.000253s : 2: opt.transform.opt_trans_graph 0.01% : 0.000136s : 4: opt.transform.symbol_engine_opt 1.00% : 0.011492s : 1: opt_a 0.03% : 0.000376s : 1: opt_after_cconv 0.08% : 0.000907s : 1: opt_after_jit_grad 0.08% : 0.000896s : 1: opt_b 5.32% : 0.060879s : 1: optimize 0.00% : 0.000054s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000022s : 1: order_py_execute_after_rewriter 0.01% : 0.000074s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000032s : 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% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000079s : 1: pre_auto_parallel 0.00% : 0.000055s : 1: py_interpret_to_execute 0.00% : 0.000042s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000114s : 1: remove_dup_value 0.32% : 0.003662s : 1: renormalize.infer 0.18% : 0.002049s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000557s : 1: rewriter_after_opt_a 0.01% : 0.000171s : 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% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000022s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000213s : 1: symbol_engine_optimizer 0.03% : 0.000293s : 1: tuple_transform 70.99% : 0.812860s : 1: type_inference mki_log delete old file:/home/jenkins/ascend/log/atb/atb_61236_20260129171906.log . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[False-False-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[False-False-bfloat16--1-shape0],max_mem:116.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:38:10.911.082 [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 = 1.2181, [21] [bootstrap]: 0.00093155 [type_inference]: 1.05467 [event_method]: 5.535e-05 [auto_monad]: 0.00016945 [graph_reusing]: 8.40999e-06 [inline]: 3.27002e-06 [add_attr]: 0.00521461, [1] [add_attr_with_inline]: 0.00519564, [1] [Cycle 1]: 0.00012506, [2] [tag_attr]: 5.859e-05 [meta_addattr_fg_expand]: 9.11998e-06 [parallel-infer-symbol]: 4.87998e-06 [pre_auto_parallel]: 6.162e-05 [insert-virtual-dataset]: 3.25e-06 [parallel-infer-symbol-second]: 1.35999e-06 [dataset_repeat_opt]: 2.63998e-06 [pipeline_split]: 1.89999e-06 [optimize]: 0.155833, [53] [py_interpret_to_execute]: 5.561e-05 [rewriter_before_opt_a]: 0.00017704 [opt_a]: 0.151245, [2] [Cycle 1]: 0.149229, [45] [expand_dump_flag]: 4.02e-06 [switch_simplify]: 6.096e-05 [loop_unroll]: 4.263e-05 [a_1]: 0.0015462 [with_stream_mark]: 4.174e-05 [recompute_prepare]: 2.789e-05 [updatestate_depend_eliminate]: 1.338e-05 [updatestate_assign_eliminate]: 1.082e-05 [updatestate_loads_eliminate]: 1.049e-05 [parameter_eliminate]: 2.63998e-06 [a_2]: 0.00033117 [accelerated_algorithm]: 5.211e-05 [shard]: 3.83999e-06 [meta_shard_fg_expand]: 1.073e-05 [shard_inline]: 2.239e-05 [merge_send_recv]: 2.007e-05 [auto_parallel]: 1.754e-05 [parallel]: 3.7e-05 [flash_sp]: 1.587e-05 [merge_comm]: 1.306e-05 [allreduce_fusion]: 1.117e-05 [matmul_add_comm_reduction]: 2.353e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 2.566e-05 [virtual_dataset]: 2.24e-05 [get_grad_eliminate_]: 2.156e-05 [virtual_output]: 2.184e-05 [merge_forward]: 1.159e-05 [cell_reuse_recompute_pass]: 2.76e-06 [offload_activation]: 2.486e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.455e-05 [merge_recompute_call_nodes]: 2.04999e-06 [before_grad]: 3.888e-05 [set_forward_comm_id_for_comm_node_pass]: 1.399e-05 [meta_fg_expand]: 1.074e-05 [flash_sp_send_recv_attached]: 6.06e-06 [receive_attached]: 2.62001e-06 [after_resolve]: 2.858e-05 [a_after_grad]: 3.56e-05 [renormalize]: 0.145834 [add_forward_monad_depend]: 1.816e-05 [auto_monad_grad]: 3.65e-06 [auto_monad_eliminator]: 4.565e-05 [cse]: 0.00019129 [a_3]: 0.00016378 [Cycle 2]: 0.00199771, [45] [expand_dump_flag]: 3.35e-06 [switch_simplify]: 2.484e-05 [loop_unroll]: 2.111e-05 [a_1]: 0.00067025 [with_stream_mark]: 2.884e-05 [recompute_prepare]: 2.206e-05 [updatestate_depend_eliminate]: 1.306e-05 [updatestate_assign_eliminate]: 9.59999e-06 [updatestate_loads_eliminate]: 1.115e-05 [parameter_eliminate]: 2.51e-06 [a_2]: 0.00029884 [accelerated_algorithm]: 2.737e-05 [shard]: 2.52001e-06 [meta_shard_fg_expand]: 6.09001e-06 [shard_inline]: 1.937e-05 [merge_send_recv]: 1.849e-05 [auto_parallel]: 1.77e-05 [parallel]: 1.146e-05 [flash_sp]: 5.04e-06 [merge_comm]: 1.223e-05 [allreduce_fusion]: 1.118e-05 [matmul_add_comm_reduction]: 2.141e-05 [allreduce_slice_to_reducescatter]: 9.80013e-07 [virtual_shard_identity]: 2.131e-05 [virtual_dataset]: 2.044e-05 [get_grad_eliminate_]: 1.915e-05 [virtual_output]: 1.991e-05 [merge_forward]: 1.208e-05 [cell_reuse_recompute_pass]: 3.38e-06 [offload_activation]: 2.31e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.872e-05 [merge_recompute_call_nodes]: 1.79e-06 [before_grad]: 3.372e-05 [set_forward_comm_id_for_comm_node_pass]: 1.26e-05 [meta_fg_expand]: 9.09e-06 [flash_sp_send_recv_attached]: 2.01e-06 [receive_attached]: 2.81e-06 [after_resolve]: 2.48e-05 [a_after_grad]: 3.128e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.19001e-06 [auto_monad_grad]: 1.89e-06 [auto_monad_eliminator]: 2.728e-05 [cse]: 7.404e-05 [a_3]: 0.00013035 [py_interpret_to_execute_after_opt_a]: 3.574e-05 [slice_cell_reuse_recomputed_activation]: 2.27999e-06 [rewriter_after_opt_a]: 0.00045611 [convert_after_rewriter]: 2.216e-05 [order_py_execute_after_rewriter]: 1.3e-05 [mutable_eliminate]: 0.00089627 [opt_b]: 0.00075449, [1] [Cycle 1]: 0.00074431, [7] [b_1]: 0.00052911 [b_2]: 2.812e-05 [updatestate_depend_eliminate]: 1.986e-05 [updatestate_assign_eliminate]: 1.098e-05 [updatestate_loads_eliminate]: 1.1e-05 [renormalize]: 6.59988e-07 [cse]: 9.947e-05 [optimize_parallel_all_gather_comm]: 4.21e-05 [overlap_param_gather]: 2.19999e-06 [cconv]: 4.635e-05 [loop_unroll]: 0.00055312 [opt_after_cconv]: 0.00026839, [1] [Cycle 1]: 0.00026082, [7] [c_1]: 0.00010626 [parameter_eliminate]: 5.76e-06 [updatestate_depend_eliminate]: 1.475e-05 [updatestate_assign_eliminate]: 1.002e-05 [updatestate_loads_eliminate]: 9.51e-06 [cse]: 7.357e-05 [renormalize]: 4.50003e-07 [remove_dup_value]: 0.00010817 [tuple_transform]: 0.00026636, [1] [Cycle 1]: 0.00026011, [4] [d_1]: 0.00021011 [none_parameter_eliminate]: 2.11e-06 [renormalize]: 1.90019e-07 [switch_simplify]: 2.184e-05 [partial_unused_args_eliminate]: 2.45002e-06 [add_recomputation]: 0.00014463 [cse_after_recomputation]: 6.458e-05, [1] [Cycle 1]: 5.782e-05, [1] [cse]: 5.115e-05 [environ_conv]: 2.055e-05 [swap_dp_allreduce_reducescatter]: 1.793e-05 [bias_add_comm_swap]: 3.18e-06 [label_micro_interleaved_index]: 5.51e-06 [label_fine_grained_interleaved_index]: 3.16999e-06 [merge_cast_opt]: 1.50001e-06 [slice_recompute_activation]: 2.04e-06 [micro_interleaved_order_control]: 2.90002e-06 [assign_add_opt]: 1.35999e-06 [ForceFp32Comm]: 1.07e-06 [remove_cast_before_assign_add]: 1.15001e-06 [full_micro_interleaved_order_control]: 2.84999e-06 [reorder_send_recv_between_fp_bp]: 2.74001e-06 [comm_op_add_attrs]: 1.17e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.32e-06 [interleave_parallel_branches]: 1.14e-06 [overlap_opt_shard_in_pipeline]: 5.88002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.29999e-06 [control_data_broadcast_order]: 3.397e-05 [grouped_pairwise_exchange_alltoall]: 1.50001e-06 [offloading_packed_experts]: 1.036e-05 [overlap_recompute_and_grad_model_parallel]: 9.72999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.17999e-06 [overlap_recompute_allgather_and_fa_grad]: 2.19999e-06 [overlap_recompute_comm]: 2.63003e-06 [overlap_grad_ring_attention]: 9.69999e-06 [overlap_grad_flash_sp]: 5.091e-05 [begin_end_overlap_inline]: 6.19999e-07 [split_matmul_comm_elemetwise]: 2.56998e-06 [split_layernorm_comm]: 2.43002e-06 [handle_group_info]: 1.15999e-06 [symbol_engine_optimizer]: 0.00018564, [1] [Cycle 1]: 0.00017985, [6] [build]: 1.749e-05 [elim_shapecalc]: 2.84e-05 [elim_not_effective]: 3.797e-05 [opt_reshape]: 2.786e-05 [fold_const_symbol]: 3.367e-05 [renormalize]: 2.19996e-07 [detach_backward]: 3.68e-06 [pipeline_parallel_scheduler]: 2.26998e-06 [auto_monad_reorder]: 4.34e-05 [get_jit_bprop_graph]: 1.94e-06 [rewriter_after_jit_bprop_graph]: 5.95002e-06 [opt_after_jit_grad]: 0.00074782 [validate]: 0.00011413 Sums bootstrap : 0.000932s : 0.08% type_inference : 1.054672s : 87.04% event_method : 0.000055s : 0.00% auto_monad : 0.000169s : 0.01% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000059s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000009s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000062s : 0.01% 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 : 0.000056s : 0.00% optimize.rewriter_before_opt_a : 0.000177s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000086s : 0.01% optimize.opt_a.loop_unroll : 0.000064s : 0.01% optimize.opt_a.a_1 : 0.002216s : 0.18% optimize.opt_a.with_stream_mark : 0.000071s : 0.01% optimize.opt_a.recompute_prepare : 0.000050s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000026s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000020s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000630s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000079s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000017s : 0.00% optimize.opt_a.shard_inline : 0.000042s : 0.00% optimize.opt_a.merge_send_recv : 0.000039s : 0.00% optimize.opt_a.auto_parallel : 0.000035s : 0.00% optimize.opt_a.parallel : 0.000048s : 0.00% optimize.opt_a.flash_sp : 0.000021s : 0.00% optimize.opt_a.merge_comm : 0.000025s : 0.00% optimize.opt_a.allreduce_fusion : 0.000022s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000045s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000047s : 0.00% optimize.opt_a.virtual_dataset : 0.000043s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000041s : 0.00% optimize.opt_a.virtual_output : 0.000042s : 0.00% optimize.opt_a.merge_forward : 0.000024s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000048s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000083s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000073s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000027s : 0.00% optimize.opt_a.meta_fg_expand : 0.000020s : 0.00% 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 : 0.000053s : 0.00% optimize.opt_a.a_after_grad : 0.000067s : 0.01% optimize.opt_a.renormalize : 0.145834s : 12.04% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000073s : 0.01% optimize.opt_a.cse : 0.000265s : 0.02% optimize.opt_a.a_3 : 0.000294s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000036s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000456s : 0.04% optimize.convert_after_rewriter : 0.000022s : 0.00% optimize.order_py_execute_after_rewriter : 0.000013s : 0.00% optimize.mutable_eliminate : 0.000896s : 0.07% optimize.opt_b.b_1 : 0.000529s : 0.04% optimize.opt_b.b_2 : 0.000028s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000099s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000042s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000046s : 0.00% optimize.loop_unroll : 0.000553s : 0.05% optimize.opt_after_cconv.c_1 : 0.000106s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.cse : 0.000074s : 0.01% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000108s : 0.01% optimize.tuple_transform.d_1 : 0.000210s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000022s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000145s : 0.01% optimize.cse_after_recomputation.cse : 0.000051s : 0.00% optimize.environ_conv : 0.000021s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000018s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 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 : 0.000006s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000034s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000010s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000051s : 0.00% 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 : 0.000017s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000028s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000038s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000028s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000034s : 0.00% 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 : 0.000043s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000748s : 0.06% validate : 0.000114s : 0.01% Time group info: ------[substitution.] 0.000826 231 5.84% : 0.000048s : 6: substitution.arithmetic_simplify 0.73% : 0.000006s : 13: substitution.elim_not_effective 2.11% : 0.000017s : 12: substitution.float_tuple_getitem_switch 0.64% : 0.000005s : 13: substitution.fold_const_symbol 1.88% : 0.000016s : 17: substitution.graph_param_transform 47.73% : 0.000394s : 7: substitution.inline 1.62% : 0.000013s : 26: substitution.j_node_and_user_rematch 3.13% : 0.000026s : 2: substitution.less_batch_normalization 1.69% : 0.000014s : 8: substitution.minmaximum_grad 0.30% : 0.000003s : 3: substitution.opt_reshape 2.40% : 0.000020s : 26: substitution.remove_not_recompute_node 0.80% : 0.000007s : 2: substitution.replace_old_param 4.53% : 0.000037s : 8: substitution.reshape_eliminate 6.66% : 0.000055s : 16: substitution.tuple_list_convert_item_index_to_positive 2.77% : 0.000023s : 16: substitution.tuple_list_get_item_const_eliminator 4.09% : 0.000034s : 16: substitution.tuple_list_get_item_depend_reorder 9.28% : 0.000077s : 24: substitution.tuple_list_get_item_eliminator 3.80% : 0.000031s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.054521 2 99.51% : 1.049312s : 1: type_inference.infer 0.49% : 0.005209s : 1: type_inference.specialize ------[replace.] 0.000075 7 100.00% : 0.000075s : 7: replace.inline ------[match.] 0.000388 7 100.00% : 0.000388s : 7: match.inline ------[predicate.] 0.000650 4346 0.89% : 0.000006s : 42: predicate.accumulaten_eliminater 0.86% : 0.000006s : 17: predicate.ad_related_special_op_eliminate 0.72% : 0.000005s : 35: predicate.addn_check_dump 0.95% : 0.000006s : 42: predicate.addn_zero_filter 0.81% : 0.000005s : 42: predicate.adjust_all_reduce_mul_add 2.12% : 0.000014s : 77: predicate.arithmetic_simplify 0.86% : 0.000006s : 42: predicate.cast_eliminate 0.75% : 0.000005s : 34: predicate.check_bprop_eliminate 0.73% : 0.000005s : 35: predicate.compare_switch_simplify 0.21% : 0.000001s : 17: predicate.const_output_eliminate 0.74% : 0.000005s : 35: predicate.depend_value_elim 0.91% : 0.000006s : 42: predicate.dict_get_item_const_eliminator 0.92% : 0.000006s : 42: predicate.dict_get_item_eliminator 0.87% : 0.000006s : 42: predicate.dict_set_item_eliminator 1.00% : 0.000007s : 34: predicate.dumpgradient_eliminate 0.20% : 0.000001s : 17: predicate.elim_not_effective 0.48% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.23% : 0.000008s : 59: predicate.environ_add_const_eliminate 1.19% : 0.000008s : 59: predicate.environ_get_add_eliminate 1.15% : 0.000007s : 59: predicate.environ_get_depend_swap 1.95% : 0.000013s : 94: predicate.environ_get_eliminate 1.27% : 0.000008s : 59: predicate.environ_get_set_eliminate 1.06% : 0.000007s : 49: predicate.exchange_switch_depend_value 1.45% : 0.000009s : 49: predicate.float_depend_g_call 0.74% : 0.000005s : 35: predicate.float_environ_get_switch 1.32% : 0.000009s : 52: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 17: predicate.fold_const_symbol 0.76% : 0.000005s : 35: predicate.get_grad_eliminate 0.23% : 0.000002s : 17: predicate.graph_param_transform 0.72% : 0.000005s : 35: predicate.incorporate_call 0.72% : 0.000005s : 35: predicate.incorporate_call_switch 5.84% : 0.000038s : 195: predicate.inline 1.04% : 0.000007s : 35: predicate.inline_without_move 0.40% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.96% : 0.000006s : 35: predicate.less_batch_normalization 1.73% : 0.000011s : 76: predicate.list_to_tuple_eliminator_ 2.39% : 0.000016s : 118: predicate.load_eliminater 0.80% : 0.000005s : 17: predicate.loop_unroll_after_grad 1.37% : 0.000009s : 63: predicate.loop_unroll_before_grad 1.71% : 0.000011s : 76: predicate.make_slice_get_slice_eliminator 0.76% : 0.000005s : 35: predicate.merge_addn 0.77% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.79% : 0.000005s : 34: predicate.mini_step_allgather_replace 0.88% : 0.000006s : 42: predicate.minmaximum_grad 1.18% : 0.000008s : 17: predicate.mutable_eliminate 0.44% : 0.000003s : 17: predicate.opt_reshape 0.42% : 0.000003s : 17: predicate.parallel_virtual_node 1.43% : 0.000009s : 49: predicate.partial_defer_inline 1.33% : 0.000009s : 59: predicate.partial_eliminate 0.94% : 0.000006s : 42: predicate.print_const_string_wrapper 0.73% : 0.000005s : 35: predicate.reduce_all_const_elim 1.16% : 0.000008s : 42: predicate.reduce_eliminate 2.39% : 0.000016s : 118: predicate.redundant_stop_gradient_eliminater 0.41% : 0.000003s : 35: predicate.remove_not_recompute_node 1.32% : 0.000009s : 76: predicate.replace_applicator 0.52% : 0.000003s : 35: predicate.replace_old_param 0.33% : 0.000002s : 17: predicate.reset_defer_inline 0.96% : 0.000006s : 42: predicate.reshape_eliminate 0.80% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.48% : 0.000003s : 17: predicate.row_tensor_eliminate 0.92% : 0.000006s : 34: predicate.same_eliminate 0.50% : 0.000003s : 35: predicate.set_cell_output_no_recompute 0.89% : 0.000006s : 35: predicate.shard_identity_eliminate 0.81% : 0.000005s : 34: predicate.special_op_eliminate 0.83% : 0.000005s : 35: predicate.specialize_transform 0.90% : 0.000006s : 34: predicate.split_environ_get_set_with_tuple_value 0.88% : 0.000006s : 35: predicate.stack_unstack_eliminate 0.41% : 0.000003s : 17: predicate.switch_call_monad_eliminater 1.11% : 0.000007s : 49: predicate.switch_defer_inline 1.83% : 0.000012s : 83: predicate.switch_layer_defer_inline 3.79% : 0.000025s : 164: predicate.switch_simplify 0.86% : 0.000006s : 42: predicate.tile_eliminate 0.87% : 0.000006s : 42: predicate.transpose_eliminate 1.85% : 0.000012s : 76: predicate.tuple_list_convert_item_index_to_positive 1.80% : 0.000012s : 76: predicate.tuple_list_get_item_const_eliminator 1.78% : 0.000012s : 76: predicate.tuple_list_get_item_depend_reorder 3.18% : 0.000021s : 111: predicate.tuple_list_get_item_eliminator 1.75% : 0.000011s : 76: predicate.tuple_list_get_set_item_eliminator 2.65% : 0.000017s : 111: predicate.tuple_list_set_item_eliminator 1.66% : 0.000011s : 76: predicate.tuple_to_list_eliminator_ 2.33% : 0.000015s : 118: predicate.updatestate_pure_node_eliminater 3.19% : 0.000021s : 153: predicate.updatestate_useless_node_eliminater 0.40% : 0.000003s : 17: predicate.value_based_eliminate 0.88% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.81% : 0.000005s : 35: predicate.virtual_output_eliminate 0.38% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.48% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.329983 54 99.26% : 0.327544s : 45: func_graph_cloner_run.FuncGraphClonerGraph 0.74% : 0.002439s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.529640 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.34% : 0.005223s : 1: add_attr 0.34% : 0.005202s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000150s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000177s : 1: auto_monad 0.00% : 0.000048s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.06% : 0.000967s : 1: bootstrap 0.00% : 0.000050s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000037s : 1: control_data_broadcast_order 0.00% : 0.000028s : 1: convert_after_rewriter 0.00% : 0.000068s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000024s : 1: environ_conv 0.00% : 0.000066s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.04% : 0.000564s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.06% : 0.000911s : 1: mutable_eliminate 0.00% : 0.000013s : 1: offloading_packed_experts 0.00% : 0.000034s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000044s : 1: opt.transform.mutable_eliminate 0.25% : 0.003790s : 78: opt.transform.opt_a 0.01% : 0.000105s : 1: opt.transform.opt_after_cconv 0.00% : 0.000076s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000522s : 28: opt.transform.opt_b 0.01% : 0.000229s : 2: opt.transform.opt_trans_graph 0.01% : 0.000124s : 4: opt.transform.symbol_engine_opt 9.89% : 0.151250s : 1: opt_a 0.02% : 0.000272s : 1: opt_after_cconv 0.05% : 0.000762s : 1: opt_after_jit_grad 0.05% : 0.000760s : 1: opt_b 10.19% : 0.155840s : 1: optimize 0.00% : 0.000046s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000016s : 1: order_py_execute_after_rewriter 0.00% : 0.000054s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000009s : 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% : 0.000006s : 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% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000067s : 1: pre_auto_parallel 0.00% : 0.000060s : 1: py_interpret_to_execute 0.00% : 0.000041s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000113s : 1: remove_dup_value 9.33% : 0.142677s : 1: renormalize.infer 0.21% : 0.003137s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000467s : 1: rewriter_after_opt_a 0.01% : 0.000182s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000021s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000189s : 1: symbol_engine_optimizer 0.02% : 0.000270s : 1: tuple_transform 68.95% : 1.054711s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[False-False-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[False-False-bfloat16--1-shape1],max_mem:120.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:38:18.219.237 [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 = 1.77525, [21] [bootstrap]: 0.00084882 [type_inference]: 1.46998 [event_method]: 7.67e-05 [auto_monad]: 0.00022114 [graph_reusing]: 8.20999e-06 [inline]: 3.26999e-06 [add_attr]: 0.00487018, [1] [add_attr_with_inline]: 0.00484967, [1] [Cycle 1]: 9.938e-05, [2] [tag_attr]: 4.137e-05 [meta_addattr_fg_expand]: 9.83998e-06 [parallel-infer-symbol]: 3.69002e-06 [pre_auto_parallel]: 5.935e-05 [insert-virtual-dataset]: 2.48e-06 [parallel-infer-symbol-second]: 8.70001e-07 [dataset_repeat_opt]: 2.02999e-06 [pipeline_split]: 1.57999e-06 [optimize]: 0.297867, [53] [py_interpret_to_execute]: 5.314e-05 [rewriter_before_opt_a]: 0.0001608 [opt_a]: 0.208596, [2] [Cycle 1]: 0.206473, [45] [expand_dump_flag]: 4.02998e-06 [switch_simplify]: 5.96e-05 [loop_unroll]: 4.364e-05 [a_1]: 0.00148646 [with_stream_mark]: 3.617e-05 [recompute_prepare]: 2.691e-05 [updatestate_depend_eliminate]: 1.408e-05 [updatestate_assign_eliminate]: 1.079e-05 [updatestate_loads_eliminate]: 1.032e-05 [parameter_eliminate]: 3.62998e-06 [a_2]: 0.00033174 [accelerated_algorithm]: 4.659e-05 [shard]: 2.64001e-06 [meta_shard_fg_expand]: 7.23999e-06 [shard_inline]: 2.174e-05 [merge_send_recv]: 1.849e-05 [auto_parallel]: 1.591e-05 [parallel]: 3.292e-05 [flash_sp]: 5.495e-05 [merge_comm]: 0.00043635 [allreduce_fusion]: 2.048e-05 [matmul_add_comm_reduction]: 3.069e-05 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 8.011e-05 [virtual_dataset]: 2.8e-05 [get_grad_eliminate_]: 2.381e-05 [virtual_output]: 2.28e-05 [merge_forward]: 1.363e-05 [cell_reuse_recompute_pass]: 3.75e-06 [offload_activation]: 2.533e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.815e-05 [merge_recompute_call_nodes]: 1.59e-06 [before_grad]: 3.912e-05 [set_forward_comm_id_for_comm_node_pass]: 1.368e-05 [meta_fg_expand]: 1.891e-05 [flash_sp_send_recv_attached]: 1.002e-05 [receive_attached]: 2.04999e-06 [after_resolve]: 2.989e-05 [a_after_grad]: 3.699e-05 [renormalize]: 0.0813126 [add_forward_monad_depend]: 1.969e-05 [auto_monad_grad]: 2.71e-06 [auto_monad_eliminator]: 4.923e-05 [cse]: 0.00021142 [a_3]: 0.00016906 [Cycle 2]: 0.00210782, [45] [expand_dump_flag]: 2.72001e-06 [switch_simplify]: 2.305e-05 [loop_unroll]: 2.075e-05 [a_1]: 0.0006613 [with_stream_mark]: 3.036e-05 [recompute_prepare]: 2.454e-05 [updatestate_depend_eliminate]: 1.335e-05 [updatestate_assign_eliminate]: 1.023e-05 [updatestate_loads_eliminate]: 9.49e-06 [parameter_eliminate]: 2.66e-06 [a_2]: 0.00029497 [accelerated_algorithm]: 2.684e-05 [shard]: 2.28998e-06 [meta_shard_fg_expand]: 6.71e-06 [shard_inline]: 1.965e-05 [merge_send_recv]: 1.829e-05 [auto_parallel]: 1.913e-05 [parallel]: 1.104e-05 [flash_sp]: 6.91001e-06 [merge_comm]: 1.219e-05 [allreduce_fusion]: 1.082e-05 [matmul_add_comm_reduction]: 2.233e-05 [allreduce_slice_to_reducescatter]: 8.50006e-07 [virtual_shard_identity]: 2.537e-05 [virtual_dataset]: 1.981e-05 [get_grad_eliminate_]: 2.083e-05 [virtual_output]: 1.939e-05 [merge_forward]: 1.206e-05 [cell_reuse_recompute_pass]: 3.35e-06 [offload_activation]: 2.432e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.286e-05 [merge_recompute_call_nodes]: 1.50001e-06 [before_grad]: 3.489e-05 [set_forward_comm_id_for_comm_node_pass]: 1.303e-05 [meta_fg_expand]: 1.007e-05 [flash_sp_send_recv_attached]: 2.35002e-06 [receive_attached]: 3.16001e-06 [after_resolve]: 4.656e-05 [a_after_grad]: 3.432e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 5.25999e-06 [auto_monad_grad]: 3.08e-06 [auto_monad_eliminator]: 3.443e-05 [cse]: 9.089e-05 [a_3]: 0.00015312 [py_interpret_to_execute_after_opt_a]: 3.954e-05 [slice_cell_reuse_recomputed_activation]: 2.76e-06 [rewriter_after_opt_a]: 0.00049405 [convert_after_rewriter]: 2.527e-05 [order_py_execute_after_rewriter]: 1.459e-05 [mutable_eliminate]: 0.00088479 [opt_b]: 0.0589497, [1] [Cycle 1]: 0.0589363, [7] [b_1]: 0.0542922 [b_2]: 3.372e-05 [updatestate_depend_eliminate]: 3.136e-05 [updatestate_assign_eliminate]: 1.006e-05 [updatestate_loads_eliminate]: 1.077e-05 [renormalize]: 1.10001e-06 [cse]: 0.00443921 [optimize_parallel_all_gather_comm]: 6.763e-05 [overlap_param_gather]: 2.51998e-06 [cconv]: 5.318e-05 [loop_unroll]: 0.00087629 [opt_after_cconv]: 0.0262457, [1] [Cycle 1]: 0.0262321, [7] [c_1]: 0.0258698 [parameter_eliminate]: 8.42e-06 [updatestate_depend_eliminate]: 3.353e-05 [updatestate_assign_eliminate]: 1.229e-05 [updatestate_loads_eliminate]: 1.038e-05 [cse]: 0.00019963 [renormalize]: 8.39995e-07 [remove_dup_value]: 0.00011993 [tuple_transform]: 0.000321, [1] [Cycle 1]: 0.00030872, [4] [d_1]: 0.00025264 [none_parameter_eliminate]: 3.18e-06 [renormalize]: 4.50003e-07 [switch_simplify]: 2.422e-05 [partial_unused_args_eliminate]: 2.79001e-06 [add_recomputation]: 0.00016058 [cse_after_recomputation]: 7.823e-05, [1] [Cycle 1]: 7.162e-05, [1] [cse]: 6.377e-05 [environ_conv]: 2.346e-05 [swap_dp_allreduce_reducescatter]: 1.828e-05 [bias_add_comm_swap]: 3.01001e-06 [label_micro_interleaved_index]: 7.98001e-06 [label_fine_grained_interleaved_index]: 2.93e-06 [merge_cast_opt]: 1.52001e-06 [slice_recompute_activation]: 2.13002e-06 [micro_interleaved_order_control]: 3.28e-06 [assign_add_opt]: 1.78002e-06 [ForceFp32Comm]: 1.20999e-06 [remove_cast_before_assign_add]: 1.12999e-06 [full_micro_interleaved_order_control]: 2.22999e-06 [reorder_send_recv_between_fp_bp]: 2.63e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 1.06002e-06 [interleave_split_concat_branches]: 1.23002e-06 [interleave_parallel_branches]: 1.06002e-06 [overlap_opt_shard_in_pipeline]: 1.27999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.76e-06 [control_data_broadcast_order]: 3.698e-05 [grouped_pairwise_exchange_alltoall]: 1.47001e-06 [offloading_packed_experts]: 1.041e-05 [overlap_recompute_and_grad_model_parallel]: 1.002e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.17999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.23002e-06 [overlap_recompute_comm]: 2.24999e-06 [overlap_grad_ring_attention]: 1.027e-05 [overlap_grad_flash_sp]: 4.916e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.52001e-06 [split_layernorm_comm]: 1.91e-06 [handle_group_info]: 1.03001e-06 [symbol_engine_optimizer]: 0.00019986, [1] [Cycle 1]: 0.00019381, [6] [build]: 1.989e-05 [elim_shapecalc]: 3.365e-05 [elim_not_effective]: 4.037e-05 [opt_reshape]: 2.852e-05 [fold_const_symbol]: 3.389e-05 [renormalize]: 2.59985e-07 [detach_backward]: 2.66e-06 [pipeline_parallel_scheduler]: 1.82001e-06 [auto_monad_reorder]: 4.258e-05 [get_jit_bprop_graph]: 1.91e-06 [rewriter_after_jit_bprop_graph]: 8.90999e-06 [opt_after_jit_grad]: 0.00089764 [validate]: 0.0001092 Sums bootstrap : 0.000849s : 0.05% type_inference : 1.469984s : 89.21% event_method : 0.000077s : 0.00% auto_monad : 0.000221s : 0.01% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000041s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000010s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000059s : 0.00% 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 : 0.000053s : 0.00% optimize.rewriter_before_opt_a : 0.000161s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000083s : 0.01% optimize.opt_a.loop_unroll : 0.000064s : 0.00% optimize.opt_a.a_1 : 0.002148s : 0.13% optimize.opt_a.with_stream_mark : 0.000067s : 0.00% optimize.opt_a.recompute_prepare : 0.000051s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000027s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000020s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000627s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000073s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000014s : 0.00% optimize.opt_a.shard_inline : 0.000041s : 0.00% optimize.opt_a.merge_send_recv : 0.000037s : 0.00% optimize.opt_a.auto_parallel : 0.000035s : 0.00% optimize.opt_a.parallel : 0.000044s : 0.00% optimize.opt_a.flash_sp : 0.000062s : 0.00% optimize.opt_a.merge_comm : 0.000449s : 0.03% optimize.opt_a.allreduce_fusion : 0.000031s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000053s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000105s : 0.01% optimize.opt_a.virtual_dataset : 0.000048s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000045s : 0.00% optimize.opt_a.virtual_output : 0.000042s : 0.00% optimize.opt_a.merge_forward : 0.000026s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000050s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000101s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000074s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000027s : 0.00% optimize.opt_a.meta_fg_expand : 0.000029s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000012s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000076s : 0.00% optimize.opt_a.a_after_grad : 0.000071s : 0.00% optimize.opt_a.renormalize : 0.081313s : 4.93% optimize.opt_a.add_forward_monad_depend : 0.000025s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000084s : 0.01% optimize.opt_a.cse : 0.000302s : 0.02% optimize.opt_a.a_3 : 0.000322s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000040s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000494s : 0.03% optimize.convert_after_rewriter : 0.000025s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000885s : 0.05% optimize.opt_b.b_1 : 0.054292s : 3.30% optimize.opt_b.b_2 : 0.000034s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000031s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.004439s : 0.27% optimize.optimize_parallel_all_gather_comm : 0.000068s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000053s : 0.00% optimize.loop_unroll : 0.000876s : 0.05% optimize.opt_after_cconv.c_1 : 0.025870s : 1.57% optimize.opt_after_cconv.parameter_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000034s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.cse : 0.000200s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000120s : 0.01% optimize.tuple_transform.d_1 : 0.000253s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000024s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000161s : 0.01% optimize.cse_after_recomputation.cse : 0.000064s : 0.00% optimize.environ_conv : 0.000023s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000018s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 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 : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000037s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000010s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000049s : 0.00% 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 : 0.000020s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000034s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000040s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000029s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000034s : 0.00% 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 : 0.000043s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000898s : 0.05% validate : 0.000109s : 0.01% Time group info: ------[substitution.] 0.000787 231 5.64% : 0.000044s : 6: substitution.arithmetic_simplify 0.82% : 0.000006s : 13: substitution.elim_not_effective 2.12% : 0.000017s : 12: substitution.float_tuple_getitem_switch 0.70% : 0.000005s : 13: substitution.fold_const_symbol 2.40% : 0.000019s : 17: substitution.graph_param_transform 42.58% : 0.000335s : 7: substitution.inline 1.83% : 0.000014s : 26: substitution.j_node_and_user_rematch 2.92% : 0.000023s : 2: substitution.less_batch_normalization 1.89% : 0.000015s : 8: substitution.minmaximum_grad 0.34% : 0.000003s : 3: substitution.opt_reshape 2.54% : 0.000020s : 26: substitution.remove_not_recompute_node 1.12% : 0.000009s : 2: substitution.replace_old_param 4.87% : 0.000038s : 8: substitution.reshape_eliminate 7.42% : 0.000058s : 16: substitution.tuple_list_convert_item_index_to_positive 3.37% : 0.000026s : 16: substitution.tuple_list_get_item_const_eliminator 4.55% : 0.000036s : 16: substitution.tuple_list_get_item_depend_reorder 10.30% : 0.000081s : 24: substitution.tuple_list_get_item_eliminator 4.58% : 0.000036s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.469719 2 97.93% : 1.439325s : 1: type_inference.infer 2.07% : 0.030394s : 1: type_inference.specialize ------[replace.] 0.000069 7 100.00% : 0.000069s : 7: replace.inline ------[match.] 0.000330 7 100.00% : 0.000330s : 7: match.inline ------[predicate.] 0.000707 4346 0.81% : 0.000006s : 42: predicate.accumulaten_eliminater 0.94% : 0.000007s : 17: predicate.ad_related_special_op_eliminate 0.68% : 0.000005s : 35: predicate.addn_check_dump 0.80% : 0.000006s : 42: predicate.addn_zero_filter 0.83% : 0.000006s : 42: predicate.adjust_all_reduce_mul_add 2.01% : 0.000014s : 77: predicate.arithmetic_simplify 0.82% : 0.000006s : 42: predicate.cast_eliminate 0.69% : 0.000005s : 34: predicate.check_bprop_eliminate 0.65% : 0.000005s : 35: predicate.compare_switch_simplify 0.33% : 0.000002s : 17: predicate.const_output_eliminate 0.66% : 0.000005s : 35: predicate.depend_value_elim 0.82% : 0.000006s : 42: predicate.dict_get_item_const_eliminator 0.88% : 0.000006s : 42: predicate.dict_get_item_eliminator 0.80% : 0.000006s : 42: predicate.dict_set_item_eliminator 0.96% : 0.000007s : 34: predicate.dumpgradient_eliminate 0.20% : 0.000001s : 17: predicate.elim_not_effective 0.48% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.12% : 0.000008s : 59: predicate.environ_add_const_eliminate 1.08% : 0.000008s : 59: predicate.environ_get_add_eliminate 1.08% : 0.000008s : 59: predicate.environ_get_depend_swap 1.83% : 0.000013s : 94: predicate.environ_get_eliminate 1.11% : 0.000008s : 59: predicate.environ_get_set_eliminate 0.93% : 0.000007s : 49: predicate.exchange_switch_depend_value 1.33% : 0.000009s : 49: predicate.float_depend_g_call 0.70% : 0.000005s : 35: predicate.float_environ_get_switch 1.14% : 0.000008s : 52: predicate.float_tuple_getitem_switch 0.17% : 0.000001s : 17: predicate.fold_const_symbol 0.81% : 0.000006s : 35: predicate.get_grad_eliminate 0.23% : 0.000002s : 17: predicate.graph_param_transform 0.66% : 0.000005s : 35: predicate.incorporate_call 0.61% : 0.000004s : 35: predicate.incorporate_call_switch 7.49% : 0.000053s : 195: predicate.inline 1.08% : 0.000008s : 35: predicate.inline_without_move 0.38% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.90% : 0.000006s : 35: predicate.less_batch_normalization 1.76% : 0.000012s : 76: predicate.list_to_tuple_eliminator_ 2.18% : 0.000015s : 118: predicate.load_eliminater 1.11% : 0.000008s : 17: predicate.loop_unroll_after_grad 1.25% : 0.000009s : 63: predicate.loop_unroll_before_grad 1.90% : 0.000013s : 76: predicate.make_slice_get_slice_eliminator 0.73% : 0.000005s : 35: predicate.merge_addn 0.70% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.77% : 0.000005s : 34: predicate.mini_step_allgather_replace 0.80% : 0.000006s : 42: predicate.minmaximum_grad 1.27% : 0.000009s : 17: predicate.mutable_eliminate 0.44% : 0.000003s : 17: predicate.opt_reshape 1.24% : 0.000009s : 17: predicate.parallel_virtual_node 1.32% : 0.000009s : 49: predicate.partial_defer_inline 1.21% : 0.000009s : 59: predicate.partial_eliminate 0.76% : 0.000005s : 42: predicate.print_const_string_wrapper 0.72% : 0.000005s : 35: predicate.reduce_all_const_elim 1.05% : 0.000007s : 42: predicate.reduce_eliminate 2.40% : 0.000017s : 118: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000004s : 35: predicate.remove_not_recompute_node 1.23% : 0.000009s : 76: predicate.replace_applicator 0.41% : 0.000003s : 35: predicate.replace_old_param 0.29% : 0.000002s : 17: predicate.reset_defer_inline 0.87% : 0.000006s : 42: predicate.reshape_eliminate 0.70% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.50% : 0.000004s : 17: predicate.row_tensor_eliminate 0.96% : 0.000007s : 34: predicate.same_eliminate 0.50% : 0.000004s : 35: predicate.set_cell_output_no_recompute 1.00% : 0.000007s : 35: predicate.shard_identity_eliminate 0.79% : 0.000006s : 34: predicate.special_op_eliminate 0.77% : 0.000005s : 35: predicate.specialize_transform 0.98% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.95% : 0.000007s : 35: predicate.stack_unstack_eliminate 0.45% : 0.000003s : 17: predicate.switch_call_monad_eliminater 1.03% : 0.000007s : 49: predicate.switch_defer_inline 1.65% : 0.000012s : 83: predicate.switch_layer_defer_inline 3.48% : 0.000025s : 164: predicate.switch_simplify 0.81% : 0.000006s : 42: predicate.tile_eliminate 0.78% : 0.000006s : 42: predicate.transpose_eliminate 1.70% : 0.000012s : 76: predicate.tuple_list_convert_item_index_to_positive 1.76% : 0.000012s : 76: predicate.tuple_list_get_item_const_eliminator 1.65% : 0.000012s : 76: predicate.tuple_list_get_item_depend_reorder 3.08% : 0.000022s : 111: predicate.tuple_list_get_item_eliminator 1.71% : 0.000012s : 76: predicate.tuple_list_get_set_item_eliminator 2.51% : 0.000018s : 111: predicate.tuple_list_set_item_eliminator 1.56% : 0.000011s : 76: predicate.tuple_to_list_eliminator_ 2.24% : 0.000016s : 118: predicate.updatestate_pure_node_eliminater 3.49% : 0.000025s : 153: predicate.updatestate_useless_node_eliminater 1.48% : 0.000010s : 17: predicate.value_based_eliminate 0.87% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.75% : 0.000005s : 35: predicate.virtual_output_eliminate 0.33% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.47% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.045383 54 31.48% : 0.014285s : 45: func_graph_cloner_run.FuncGraphClonerGraph 68.52% : 0.031098s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.243536 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.22% : 0.004877s : 1: add_attr 0.22% : 0.004855s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000166s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000230s : 1: auto_monad 0.00% : 0.000047s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.04% : 0.000895s : 1: bootstrap 0.00% : 0.000058s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000041s : 1: control_data_broadcast_order 0.00% : 0.000032s : 1: convert_after_rewriter 0.00% : 0.000083s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000027s : 1: environ_conv 0.00% : 0.000087s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.04% : 0.000892s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.04% : 0.000901s : 1: mutable_eliminate 0.00% : 0.000013s : 1: offloading_packed_experts 0.00% : 0.000048s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000049s : 1: opt.transform.mutable_eliminate 0.17% : 0.003831s : 78: opt.transform.opt_a 1.15% : 0.025862s : 1: opt.transform.opt_after_cconv 0.00% : 0.000079s : 1: opt.transform.opt_after_jit_grad 2.42% : 0.054259s : 28: opt.transform.opt_b 0.01% : 0.000271s : 2: opt.transform.opt_trans_graph 0.01% : 0.000131s : 4: opt.transform.symbol_engine_opt 9.30% : 0.208600s : 1: opt_a 1.17% : 0.026252s : 1: opt_after_cconv 0.04% : 0.000915s : 1: opt_after_jit_grad 2.63% : 0.058958s : 1: opt_b 13.28% : 0.297874s : 1: optimize 0.00% : 0.000074s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000053s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.00% : 0.000065s : 1: pre_auto_parallel 0.00% : 0.000059s : 1: py_interpret_to_execute 0.00% : 0.000045s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000126s : 1: remove_dup_value 1.76% : 0.039552s : 1: renormalize.infer 1.86% : 0.041726s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000506s : 1: rewriter_after_opt_a 0.01% : 0.000166s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000022s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000203s : 1: symbol_engine_optimizer 0.01% : 0.000325s : 1: tuple_transform 65.52% : 1.470021s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[False-False-bfloat16--1-shape2] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[False-False-bfloat16--1-shape2],max_mem:120.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:38:25.470.87 [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 = 1.72783, [21] [bootstrap]: 0.00084748 [type_inference]: 1.30405 [event_method]: 6.229e-05 [auto_monad]: 0.00019298 [graph_reusing]: 9.13002e-06 [inline]: 4.73001e-06 [add_attr]: 0.00514192, [1] [add_attr_with_inline]: 0.0051216, [1] [Cycle 1]: 0.00011259, [2] [tag_attr]: 5.097e-05 [meta_addattr_fg_expand]: 8.77e-06 [parallel-infer-symbol]: 3.98999e-06 [pre_auto_parallel]: 6.428e-05 [insert-virtual-dataset]: 2.47001e-06 [parallel-infer-symbol-second]: 7.2e-07 [dataset_repeat_opt]: 2.51e-06 [pipeline_split]: 1.49e-06 [optimize]: 0.231874, [53] [py_interpret_to_execute]: 5.465e-05 [rewriter_before_opt_a]: 0.00017428 [opt_a]: 0.226753, [2] [Cycle 1]: 0.22447, [45] [expand_dump_flag]: 4.56002e-06 [switch_simplify]: 6.368e-05 [loop_unroll]: 4.415e-05 [a_1]: 0.213359 [with_stream_mark]: 5.401e-05 [recompute_prepare]: 3.582e-05 [updatestate_depend_eliminate]: 1.628e-05 [updatestate_assign_eliminate]: 1.083e-05 [updatestate_loads_eliminate]: 9.84001e-06 [parameter_eliminate]: 3.9e-06 [a_2]: 0.00037683 [accelerated_algorithm]: 5.926e-05 [shard]: 3.88999e-06 [meta_shard_fg_expand]: 1.067e-05 [shard_inline]: 2.439e-05 [merge_send_recv]: 2.037e-05 [auto_parallel]: 2.109e-05 [parallel]: 3.646e-05 [flash_sp]: 1.938e-05 [merge_comm]: 1.252e-05 [allreduce_fusion]: 1.23e-05 [matmul_add_comm_reduction]: 2.604e-05 [allreduce_slice_to_reducescatter]: 1.07e-06 [virtual_shard_identity]: 3.047e-05 [virtual_dataset]: 2.467e-05 [get_grad_eliminate_]: 2.495e-05 [virtual_output]: 2.309e-05 [merge_forward]: 1.436e-05 [cell_reuse_recompute_pass]: 2.64001e-06 [offload_activation]: 2.654e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.919e-05 [merge_recompute_call_nodes]: 2.41e-06 [before_grad]: 4.191e-05 [set_forward_comm_id_for_comm_node_pass]: 1.491e-05 [meta_fg_expand]: 1.295e-05 [flash_sp_send_recv_attached]: 6.17001e-06 [receive_attached]: 2.59001e-06 [after_resolve]: 3.643e-05 [a_after_grad]: 3.908e-05 [renormalize]: 0.0088977 [add_forward_monad_depend]: 2.447e-05 [auto_monad_grad]: 3.18998e-06 [auto_monad_eliminator]: 5.586e-05 [cse]: 0.00030392 [a_3]: 0.00017917 [Cycle 2]: 0.00226294, [45] [expand_dump_flag]: 3.94002e-06 [switch_simplify]: 2.445e-05 [loop_unroll]: 2.252e-05 [a_1]: 0.00070197 [with_stream_mark]: 4.053e-05 [recompute_prepare]: 2.543e-05 [updatestate_depend_eliminate]: 1.64e-05 [updatestate_assign_eliminate]: 9.73002e-06 [updatestate_loads_eliminate]: 1.064e-05 [parameter_eliminate]: 3.37002e-06 [a_2]: 0.00032055 [accelerated_algorithm]: 3.365e-05 [shard]: 3.38e-06 [meta_shard_fg_expand]: 1.105e-05 [shard_inline]: 2.012e-05 [merge_send_recv]: 2.338e-05 [auto_parallel]: 2.146e-05 [parallel]: 1.458e-05 [flash_sp]: 7.10002e-06 [merge_comm]: 1.313e-05 [allreduce_fusion]: 1.108e-05 [matmul_add_comm_reduction]: 2.393e-05 [allreduce_slice_to_reducescatter]: 1.14003e-06 [virtual_shard_identity]: 2.403e-05 [virtual_dataset]: 2.004e-05 [get_grad_eliminate_]: 2.089e-05 [virtual_output]: 1.964e-05 [merge_forward]: 1.412e-05 [cell_reuse_recompute_pass]: 4.43001e-06 [offload_activation]: 2.994e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.916e-05 [merge_recompute_call_nodes]: 1.84e-06 [before_grad]: 3.65e-05 [set_forward_comm_id_for_comm_node_pass]: 1.443e-05 [meta_fg_expand]: 1.249e-05 [flash_sp_send_recv_attached]: 2.53e-06 [receive_attached]: 2.78e-06 [after_resolve]: 2.71e-05 [a_after_grad]: 3.394e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 5.02e-06 [auto_monad_grad]: 2.90002e-06 [auto_monad_eliminator]: 3.562e-05 [cse]: 0.00010836 [a_3]: 0.00014655 [py_interpret_to_execute_after_opt_a]: 4.282e-05 [slice_cell_reuse_recomputed_activation]: 4.3e-06 [rewriter_after_opt_a]: 0.00053413 [convert_after_rewriter]: 2.694e-05 [order_py_execute_after_rewriter]: 1.413e-05 [mutable_eliminate]: 0.00099997 [opt_b]: 0.00078754, [1] [Cycle 1]: 0.00077757, [7] [b_1]: 0.00054253 [b_2]: 2.52e-05 [updatestate_depend_eliminate]: 2.334e-05 [updatestate_assign_eliminate]: 1.107e-05 [updatestate_loads_eliminate]: 1.083e-05 [renormalize]: 8.2e-07 [cse]: 0.00011486 [optimize_parallel_all_gather_comm]: 4.912e-05 [overlap_param_gather]: 2.59999e-06 [cconv]: 5.467e-05 [loop_unroll]: 0.00068698 [opt_after_cconv]: 0.0003259, [1] [Cycle 1]: 0.00031627, [7] [c_1]: 0.0001285 [parameter_eliminate]: 7.01001e-06 [updatestate_depend_eliminate]: 2.446e-05 [updatestate_assign_eliminate]: 1.35e-05 [updatestate_loads_eliminate]: 9.54e-06 [cse]: 9.079e-05 [renormalize]: 7.89994e-07 [remove_dup_value]: 0.00011992 [tuple_transform]: 0.00028505, [1] [Cycle 1]: 0.00027848, [4] [d_1]: 0.00022914 [none_parameter_eliminate]: 2.58998e-06 [renormalize]: 2.80008e-07 [switch_simplify]: 2.262e-05 [partial_unused_args_eliminate]: 2.39999e-06 [add_recomputation]: 0.00016023 [cse_after_recomputation]: 7.985e-05, [1] [Cycle 1]: 7.452e-05, [1] [cse]: 6.429e-05 [environ_conv]: 2.525e-05 [swap_dp_allreduce_reducescatter]: 1.818e-05 [bias_add_comm_swap]: 4.08001e-06 [label_micro_interleaved_index]: 6.74999e-06 [label_fine_grained_interleaved_index]: 4.43001e-06 [merge_cast_opt]: 1.37999e-06 [slice_recompute_activation]: 2.27001e-06 [micro_interleaved_order_control]: 3.06999e-06 [assign_add_opt]: 1.46998e-06 [ForceFp32Comm]: 1.19e-06 [remove_cast_before_assign_add]: 1.29e-06 [full_micro_interleaved_order_control]: 2.41e-06 [reorder_send_recv_between_fp_bp]: 2.71999e-06 [comm_op_add_attrs]: 1.44e-06 [add_comm_op_reuse_tag]: 1.64e-06 [interleave_split_concat_branches]: 1.32999e-06 [interleave_parallel_branches]: 1.14e-06 [overlap_opt_shard_in_pipeline]: 1.33002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.04e-06 [control_data_broadcast_order]: 3.753e-05 [grouped_pairwise_exchange_alltoall]: 1.60001e-06 [offloading_packed_experts]: 1.033e-05 [overlap_recompute_and_grad_model_parallel]: 9.27001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.24e-06 [overlap_recompute_allgather_and_fa_grad]: 1.39e-06 [overlap_recompute_comm]: 2.11e-06 [overlap_grad_ring_attention]: 1.033e-05 [overlap_grad_flash_sp]: 4.948e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.44001e-06 [split_layernorm_comm]: 1.89999e-06 [handle_group_info]: 1.15999e-06 [symbol_engine_optimizer]: 0.0002067, [1] [Cycle 1]: 0.00019934, [6] [build]: 2.187e-05 [elim_shapecalc]: 3.454e-05 [elim_not_effective]: 4.149e-05 [opt_reshape]: 2.952e-05 [fold_const_symbol]: 3.343e-05 [renormalize]: 1.8999e-07 [detach_backward]: 3.03e-06 [pipeline_parallel_scheduler]: 1.83002e-06 [auto_monad_reorder]: 4.639e-05 [get_jit_bprop_graph]: 1.92001e-06 [rewriter_after_jit_bprop_graph]: 7.87e-06 [opt_after_jit_grad]: 0.185125 [validate]: 0.0001293 Sums bootstrap : 0.000847s : 0.05% type_inference : 1.304054s : 75.76% event_method : 0.000062s : 0.00% auto_monad : 0.000193s : 0.01% graph_reusing : 0.000009s : 0.00% inline : 0.000005s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000051s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000009s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000064s : 0.00% insert-virtual-dataset : 0.000002s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000001s : 0.00% optimize.py_interpret_to_execute : 0.000055s : 0.00% optimize.rewriter_before_opt_a : 0.000174s : 0.01% optimize.opt_a.expand_dump_flag : 0.000009s : 0.00% optimize.opt_a.switch_simplify : 0.000088s : 0.01% optimize.opt_a.loop_unroll : 0.000067s : 0.00% optimize.opt_a.a_1 : 0.214061s : 12.44% optimize.opt_a.with_stream_mark : 0.000095s : 0.01% optimize.opt_a.recompute_prepare : 0.000061s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000033s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000020s : 0.00% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.000697s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000093s : 0.01% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000022s : 0.00% optimize.opt_a.shard_inline : 0.000045s : 0.00% optimize.opt_a.merge_send_recv : 0.000044s : 0.00% optimize.opt_a.auto_parallel : 0.000043s : 0.00% optimize.opt_a.parallel : 0.000051s : 0.00% optimize.opt_a.flash_sp : 0.000026s : 0.00% optimize.opt_a.merge_comm : 0.000026s : 0.00% optimize.opt_a.allreduce_fusion : 0.000023s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000050s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000055s : 0.00% optimize.opt_a.virtual_dataset : 0.000045s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000046s : 0.00% optimize.opt_a.virtual_output : 0.000043s : 0.00% optimize.opt_a.merge_forward : 0.000028s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000056s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000098s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000078s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000029s : 0.00% optimize.opt_a.meta_fg_expand : 0.000025s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000064s : 0.00% optimize.opt_a.a_after_grad : 0.000073s : 0.00% optimize.opt_a.renormalize : 0.008898s : 0.52% optimize.opt_a.add_forward_monad_depend : 0.000029s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000091s : 0.01% optimize.opt_a.cse : 0.000412s : 0.02% optimize.opt_a.a_3 : 0.000326s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000043s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000004s : 0.00% optimize.rewriter_after_opt_a : 0.000534s : 0.03% optimize.convert_after_rewriter : 0.000027s : 0.00% optimize.order_py_execute_after_rewriter : 0.000014s : 0.00% optimize.mutable_eliminate : 0.001000s : 0.06% optimize.opt_b.b_1 : 0.000543s : 0.03% optimize.opt_b.b_2 : 0.000025s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000115s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000049s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000055s : 0.00% optimize.loop_unroll : 0.000687s : 0.04% optimize.opt_after_cconv.c_1 : 0.000128s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.cse : 0.000091s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000120s : 0.01% optimize.tuple_transform.d_1 : 0.000229s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000023s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000160s : 0.01% optimize.cse_after_recomputation.cse : 0.000064s : 0.00% optimize.environ_conv : 0.000025s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000018s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000004s : 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 : 0.000002s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000038s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000010s : 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 : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000049s : 0.00% 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 : 0.000022s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000035s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000041s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000030s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000033s : 0.00% 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 : 0.000046s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.185125s : 10.76% validate : 0.000129s : 0.01% Time group info: ------[substitution.] 0.001136 231 5.74% : 0.000065s : 6: substitution.arithmetic_simplify 0.55% : 0.000006s : 13: substitution.elim_not_effective 1.61% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.44% : 0.000005s : 13: substitution.fold_const_symbol 1.46% : 0.000017s : 17: substitution.graph_param_transform 51.79% : 0.000588s : 7: substitution.inline 1.23% : 0.000014s : 26: substitution.j_node_and_user_rematch 2.60% : 0.000030s : 2: substitution.less_batch_normalization 3.23% : 0.000037s : 8: substitution.minmaximum_grad 0.23% : 0.000003s : 3: substitution.opt_reshape 1.95% : 0.000022s : 26: substitution.remove_not_recompute_node 0.73% : 0.000008s : 2: substitution.replace_old_param 4.22% : 0.000048s : 8: substitution.reshape_eliminate 5.78% : 0.000066s : 16: substitution.tuple_list_convert_item_index_to_positive 2.55% : 0.000029s : 16: substitution.tuple_list_get_item_const_eliminator 3.68% : 0.000042s : 16: substitution.tuple_list_get_item_depend_reorder 8.54% : 0.000097s : 24: substitution.tuple_list_get_item_eliminator 3.67% : 0.000042s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.303872 2 99.51% : 1.297419s : 1: type_inference.infer 0.49% : 0.006453s : 1: type_inference.specialize ------[replace.] 0.000114 7 100.00% : 0.000114s : 7: replace.inline ------[match.] 0.000579 7 100.00% : 0.000579s : 7: match.inline ------[predicate.] 0.212053 4346 0.00% : 0.000007s : 42: predicate.accumulaten_eliminater 0.01% : 0.000013s : 17: predicate.ad_related_special_op_eliminate 0.00% : 0.000006s : 35: predicate.addn_check_dump 0.00% : 0.000006s : 42: predicate.addn_zero_filter 0.00% : 0.000006s : 42: predicate.adjust_all_reduce_mul_add 0.01% : 0.000018s : 77: predicate.arithmetic_simplify 0.01% : 0.000011s : 42: predicate.cast_eliminate 0.00% : 0.000005s : 34: predicate.check_bprop_eliminate 0.00% : 0.000005s : 35: predicate.compare_switch_simplify 0.00% : 0.000001s : 17: predicate.const_output_eliminate 0.00% : 0.000005s : 35: predicate.depend_value_elim 0.00% : 0.000007s : 42: predicate.dict_get_item_const_eliminator 0.00% : 0.000007s : 42: predicate.dict_get_item_eliminator 0.00% : 0.000006s : 42: predicate.dict_set_item_eliminator 0.00% : 0.000009s : 34: predicate.dumpgradient_eliminate 0.00% : 0.000001s : 17: predicate.elim_not_effective 0.00% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 99.65% : 0.211302s : 59: predicate.environ_add_const_eliminate 0.00% : 0.000008s : 59: predicate.environ_get_add_eliminate 0.00% : 0.000009s : 59: predicate.environ_get_depend_swap 0.01% : 0.000014s : 94: predicate.environ_get_eliminate 0.00% : 0.000009s : 59: predicate.environ_get_set_eliminate 0.00% : 0.000007s : 49: predicate.exchange_switch_depend_value 0.01% : 0.000012s : 49: predicate.float_depend_g_call 0.00% : 0.000007s : 35: predicate.float_environ_get_switch 0.00% : 0.000009s : 52: predicate.float_tuple_getitem_switch 0.00% : 0.000001s : 17: predicate.fold_const_symbol 0.00% : 0.000006s : 35: predicate.get_grad_eliminate 0.00% : 0.000002s : 17: predicate.graph_param_transform 0.00% : 0.000005s : 35: predicate.incorporate_call 0.00% : 0.000005s : 35: predicate.incorporate_call_switch 0.02% : 0.000044s : 195: predicate.inline 0.00% : 0.000008s : 35: predicate.inline_without_move 0.00% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.00% : 0.000007s : 35: predicate.less_batch_normalization 0.01% : 0.000012s : 76: predicate.list_to_tuple_eliminator_ 0.01% : 0.000018s : 118: predicate.load_eliminater 0.00% : 0.000007s : 17: predicate.loop_unroll_after_grad 0.00% : 0.000009s : 63: predicate.loop_unroll_before_grad 0.01% : 0.000014s : 76: predicate.make_slice_get_slice_eliminator 0.00% : 0.000006s : 35: predicate.merge_addn 0.00% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.00% : 0.000005s : 34: predicate.mini_step_allgather_replace 0.00% : 0.000007s : 42: predicate.minmaximum_grad 0.01% : 0.000012s : 17: predicate.mutable_eliminate 0.00% : 0.000003s : 17: predicate.opt_reshape 0.00% : 0.000003s : 17: predicate.parallel_virtual_node 0.01% : 0.000018s : 49: predicate.partial_defer_inline 0.00% : 0.000009s : 59: predicate.partial_eliminate 0.00% : 0.000006s : 42: predicate.print_const_string_wrapper 0.00% : 0.000006s : 35: predicate.reduce_all_const_elim 0.00% : 0.000009s : 42: predicate.reduce_eliminate 0.01% : 0.000018s : 118: predicate.redundant_stop_gradient_eliminater 0.00% : 0.000003s : 35: predicate.remove_not_recompute_node 0.00% : 0.000010s : 76: predicate.replace_applicator 0.00% : 0.000003s : 35: predicate.replace_old_param 0.00% : 0.000002s : 17: predicate.reset_defer_inline 0.00% : 0.000008s : 42: predicate.reshape_eliminate 0.00% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.00% : 0.000003s : 17: predicate.row_tensor_eliminate 0.00% : 0.000009s : 34: predicate.same_eliminate 0.00% : 0.000004s : 35: predicate.set_cell_output_no_recompute 0.00% : 0.000007s : 35: predicate.shard_identity_eliminate 0.00% : 0.000006s : 34: predicate.special_op_eliminate 0.00% : 0.000006s : 35: predicate.specialize_transform 0.00% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.00% : 0.000007s : 35: predicate.stack_unstack_eliminate 0.00% : 0.000003s : 17: predicate.switch_call_monad_eliminater 0.00% : 0.000009s : 49: predicate.switch_defer_inline 0.01% : 0.000012s : 83: predicate.switch_layer_defer_inline 0.01% : 0.000027s : 164: predicate.switch_simplify 0.00% : 0.000007s : 42: predicate.tile_eliminate 0.00% : 0.000007s : 42: predicate.transpose_eliminate 0.01% : 0.000015s : 76: predicate.tuple_list_convert_item_index_to_positive 0.01% : 0.000014s : 76: predicate.tuple_list_get_item_const_eliminator 0.01% : 0.000012s : 76: predicate.tuple_list_get_item_depend_reorder 0.01% : 0.000022s : 111: predicate.tuple_list_get_item_eliminator 0.01% : 0.000013s : 76: predicate.tuple_list_get_set_item_eliminator 0.01% : 0.000018s : 111: predicate.tuple_list_set_item_eliminator 0.01% : 0.000012s : 76: predicate.tuple_to_list_eliminator_ 0.01% : 0.000016s : 118: predicate.updatestate_pure_node_eliminater 0.01% : 0.000022s : 153: predicate.updatestate_useless_node_eliminater 0.00% : 0.000003s : 17: predicate.value_based_eliminate 0.00% : 0.000007s : 35: predicate.virtual_dataset_eliminate 0.00% : 0.000006s : 35: predicate.virtual_output_eliminate 0.00% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.00% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.009398 54 74.04% : 0.006958s : 45: func_graph_cloner_run.FuncGraphClonerGraph 25.96% : 0.002440s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.190486 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.24% : 0.005150s : 1: add_attr 0.23% : 0.005128s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000166s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000204s : 1: auto_monad 0.00% : 0.000051s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.04% : 0.000895s : 1: bootstrap 0.00% : 0.000059s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000042s : 1: control_data_broadcast_order 0.00% : 0.000033s : 1: convert_after_rewriter 0.00% : 0.000083s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000029s : 1: environ_conv 0.00% : 0.000072s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000008s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.03% : 0.000700s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.05% : 0.001015s : 1: mutable_eliminate 0.00% : 0.000013s : 1: offloading_packed_experts 0.00% : 0.000043s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000055s : 1: opt.transform.mutable_eliminate 9.85% : 0.215786s : 78: opt.transform.opt_a 0.01% : 0.000126s : 1: opt.transform.opt_after_cconv 0.01% : 0.000118s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000527s : 28: opt.transform.opt_b 0.01% : 0.000247s : 2: opt.transform.opt_trans_graph 0.01% : 0.000133s : 4: opt.transform.symbol_engine_opt 10.35% : 0.226758s : 1: opt_a 0.02% : 0.000330s : 1: opt_after_cconv 8.45% : 0.185152s : 1: opt_after_jit_grad 0.04% : 0.000792s : 1: opt_b 10.59% : 0.231881s : 1: optimize 0.00% : 0.000054s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000053s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 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% : 0.000012s : 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% : 0.000008s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.00% : 0.000069s : 1: pre_auto_parallel 0.00% : 0.000061s : 1: py_interpret_to_execute 0.00% : 0.000049s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000126s : 1: remove_dup_value 0.26% : 0.005601s : 1: renormalize.infer 0.15% : 0.003275s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000546s : 1: rewriter_after_opt_a 0.01% : 0.000180s : 1: rewriter_before_opt_a 0.00% : 0.000009s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000022s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000210s : 1: symbol_engine_optimizer 0.01% : 0.000289s : 1: tuple_transform 59.53% : 1.304093s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[False-False-bfloat16--1-shape3] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[False-False-bfloat16--1-shape3],max_mem:116.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:38:30.645.828 [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 = 2.45381, [21] [bootstrap]: 0.00090586 [type_inference]: 1.93242 [event_method]: 0.00026245 [auto_monad]: 0.00067761 [graph_reusing]: 7.914e-05 [inline]: 4.08001e-06 [add_attr]: 0.00613709, [1] [add_attr_with_inline]: 0.00611673, [1] [Cycle 1]: 0.00045592, [2] [tag_attr]: 0.0003372 [meta_addattr_fg_expand]: 6.106e-05 [parallel-infer-symbol]: 4.3e-06 [pre_auto_parallel]: 0.0003266 [insert-virtual-dataset]: 2.53e-06 [parallel-infer-symbol-second]: 1.39003e-06 [dataset_repeat_opt]: 2.41998e-06 [pipeline_split]: 1.79e-06 [optimize]: 0.511765, [53] [py_interpret_to_execute]: 0.00029307 [rewriter_before_opt_a]: 0.00086646 [opt_a]: 0.504538, [2] [Cycle 1]: 0.502052, [45] [expand_dump_flag]: 3.187e-05 [switch_simplify]: 0.00088261 [loop_unroll]: 0.00028357 [a_1]: 0.197844 [with_stream_mark]: 0.00013353 [recompute_prepare]: 4.843e-05 [updatestate_depend_eliminate]: 2.678e-05 [updatestate_assign_eliminate]: 1.759e-05 [updatestate_loads_eliminate]: 1.813e-05 [parameter_eliminate]: 3.9e-06 [a_2]: 0.00095114 [accelerated_algorithm]: 6.656e-05 [shard]: 2.70997e-06 [meta_shard_fg_expand]: 3.392e-05 [shard_inline]: 2.645e-05 [merge_send_recv]: 2.192e-05 [auto_parallel]: 2.206e-05 [parallel]: 3.367e-05 [flash_sp]: 1.686e-05 [merge_comm]: 1.639e-05 [allreduce_fusion]: 1.445e-05 [matmul_add_comm_reduction]: 2.447e-05 [allreduce_slice_to_reducescatter]: 8.2e-07 [virtual_shard_identity]: 3.127e-05 [virtual_dataset]: 2.498e-05 [get_grad_eliminate_]: 2.422e-05 [virtual_output]: 2.495e-05 [merge_forward]: 1.448e-05 [cell_reuse_recompute_pass]: 2.29001e-06 [offload_activation]: 2.508e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.416e-05 [merge_recompute_call_nodes]: 1.42e-06 [before_grad]: 4.512e-05 [set_forward_comm_id_for_comm_node_pass]: 1.565e-05 [meta_fg_expand]: 2.107e-05 [flash_sp_send_recv_attached]: 5.79e-06 [receive_attached]: 3.40998e-06 [after_resolve]: 3.086e-05 [a_after_grad]: 3.991e-05 [renormalize]: 0.30017 [add_forward_monad_depend]: 2.237e-05 [auto_monad_grad]: 3.47997e-06 [auto_monad_eliminator]: 6.244e-05 [cse]: 0.00029179 [a_3]: 0.00018549 [Cycle 2]: 0.00246577, [45] [expand_dump_flag]: 3.48999e-06 [switch_simplify]: 2.626e-05 [loop_unroll]: 2.441e-05 [a_1]: 0.00080595 [with_stream_mark]: 3.724e-05 [recompute_prepare]: 2.742e-05 [updatestate_depend_eliminate]: 1.626e-05 [updatestate_assign_eliminate]: 1.253e-05 [updatestate_loads_eliminate]: 1.163e-05 [parameter_eliminate]: 2.28998e-06 [a_2]: 0.00034643 [accelerated_algorithm]: 3.494e-05 [shard]: 3.02002e-06 [meta_shard_fg_expand]: 9.28002e-06 [shard_inline]: 2.328e-05 [merge_send_recv]: 2.263e-05 [auto_parallel]: 2.086e-05 [parallel]: 1.126e-05 [flash_sp]: 6.12999e-06 [merge_comm]: 1.436e-05 [allreduce_fusion]: 1.404e-05 [matmul_add_comm_reduction]: 2.525e-05 [allreduce_slice_to_reducescatter]: 1.35001e-06 [virtual_shard_identity]: 7.962e-05 [virtual_dataset]: 2.658e-05 [get_grad_eliminate_]: 2.372e-05 [virtual_output]: 2.414e-05 [merge_forward]: 1.648e-05 [cell_reuse_recompute_pass]: 3.55998e-06 [offload_activation]: 2.719e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.235e-05 [merge_recompute_call_nodes]: 1.74e-06 [before_grad]: 4.384e-05 [set_forward_comm_id_for_comm_node_pass]: 1.649e-05 [meta_fg_expand]: 1.287e-05 [flash_sp_send_recv_attached]: 2.12001e-06 [receive_attached]: 2.54001e-06 [after_resolve]: 2.938e-05 [a_after_grad]: 3.752e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 4.19002e-06 [auto_monad_grad]: 1.91998e-06 [auto_monad_eliminator]: 3.885e-05 [cse]: 0.00010548 [a_3]: 0.0001573 [py_interpret_to_execute_after_opt_a]: 3.825e-05 [slice_cell_reuse_recomputed_activation]: 2.02001e-06 [rewriter_after_opt_a]: 0.00102433 [convert_after_rewriter]: 3.309e-05 [order_py_execute_after_rewriter]: 1.546e-05 [mutable_eliminate]: 0.00097302 [opt_b]: 0.00085803, [1] [Cycle 1]: 0.0008487, [7] [b_1]: 0.00060368 [b_2]: 3.024e-05 [updatestate_depend_eliminate]: 2.167e-05 [updatestate_assign_eliminate]: 1.255e-05 [updatestate_loads_eliminate]: 1.182e-05 [renormalize]: 8.70001e-07 [cse]: 0.00012454 [optimize_parallel_all_gather_comm]: 4.514e-05 [overlap_param_gather]: 1.89e-06 [cconv]: 4.594e-05 [loop_unroll]: 0.00057276 [opt_after_cconv]: 0.00045034, [1] [Cycle 1]: 0.00044158, [7] [c_1]: 0.0001191 [parameter_eliminate]: 5.59e-06 [updatestate_depend_eliminate]: 1.871e-05 [updatestate_assign_eliminate]: 1.177e-05 [updatestate_loads_eliminate]: 1.127e-05 [cse]: 0.00022839 [renormalize]: 8.39995e-07 [remove_dup_value]: 0.00014001 [tuple_transform]: 0.00030122, [1] [Cycle 1]: 0.00029236, [4] [d_1]: 0.00024252 [none_parameter_eliminate]: 2.70002e-06 [renormalize]: 2.50002e-07 [switch_simplify]: 2.462e-05 [partial_unused_args_eliminate]: 1.92001e-06 [add_recomputation]: 0.0001728 [cse_after_recomputation]: 9.013e-05, [1] [Cycle 1]: 8.372e-05, [1] [cse]: 7.522e-05 [environ_conv]: 2.357e-05 [swap_dp_allreduce_reducescatter]: 2.689e-05 [bias_add_comm_swap]: 3.50003e-06 [label_micro_interleaved_index]: 5.80002e-06 [label_fine_grained_interleaved_index]: 3.5e-06 [merge_cast_opt]: 1.45001e-06 [slice_recompute_activation]: 2.22999e-06 [micro_interleaved_order_control]: 2.91999e-06 [assign_add_opt]: 1.34e-06 [ForceFp32Comm]: 1.35999e-06 [remove_cast_before_assign_add]: 1.15001e-06 [full_micro_interleaved_order_control]: 2.16998e-06 [reorder_send_recv_between_fp_bp]: 2.71999e-06 [comm_op_add_attrs]: 1.02e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.20999e-06 [interleave_parallel_branches]: 1.10001e-06 [overlap_opt_shard_in_pipeline]: 1.20999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.64e-06 [control_data_broadcast_order]: 4.766e-05 [grouped_pairwise_exchange_alltoall]: 1.92999e-06 [offloading_packed_experts]: 1.132e-05 [overlap_recompute_and_grad_model_parallel]: 1.191e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.27e-06 [overlap_recompute_allgather_and_fa_grad]: 1.34e-06 [overlap_recompute_comm]: 2.52001e-06 [overlap_grad_ring_attention]: 1.133e-05 [overlap_grad_flash_sp]: 5.755e-05 [begin_end_overlap_inline]: 5.50004e-07 [split_matmul_comm_elemetwise]: 2.64999e-06 [split_layernorm_comm]: 1.77999e-06 [handle_group_info]: 8.99978e-07 [symbol_engine_optimizer]: 0.00073752, [1] [Cycle 1]: 0.00073058, [6] [build]: 0.00028687 [elim_shapecalc]: 3.808e-05 [elim_not_effective]: 7.458e-05 [opt_reshape]: 0.00019359 [fold_const_symbol]: 6.289e-05 [renormalize]: 6.69999e-07 [detach_backward]: 3.58999e-06 [pipeline_parallel_scheduler]: 1.91e-06 [auto_monad_reorder]: 6.132e-05 [get_jit_bprop_graph]: 2.13002e-06 [rewriter_after_jit_bprop_graph]: 6.33e-06 [opt_after_jit_grad]: 0.00078762 [validate]: 9.993e-05 Sums bootstrap : 0.000906s : 0.04% type_inference : 1.932417s : 78.99% event_method : 0.000262s : 0.01% auto_monad : 0.000678s : 0.03% graph_reusing : 0.000079s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000337s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000061s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000327s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000293s : 0.01% optimize.rewriter_before_opt_a : 0.000866s : 0.04% optimize.opt_a.expand_dump_flag : 0.000035s : 0.00% optimize.opt_a.switch_simplify : 0.000909s : 0.04% optimize.opt_a.loop_unroll : 0.000308s : 0.01% optimize.opt_a.a_1 : 0.198650s : 8.12% optimize.opt_a.with_stream_mark : 0.000171s : 0.01% optimize.opt_a.recompute_prepare : 0.000076s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000043s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000030s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000030s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001298s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000102s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000043s : 0.00% optimize.opt_a.shard_inline : 0.000050s : 0.00% optimize.opt_a.merge_send_recv : 0.000045s : 0.00% optimize.opt_a.auto_parallel : 0.000043s : 0.00% optimize.opt_a.parallel : 0.000045s : 0.00% optimize.opt_a.flash_sp : 0.000023s : 0.00% optimize.opt_a.merge_comm : 0.000031s : 0.00% optimize.opt_a.allreduce_fusion : 0.000028s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000050s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000111s : 0.00% optimize.opt_a.virtual_dataset : 0.000052s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000048s : 0.00% optimize.opt_a.virtual_output : 0.000049s : 0.00% optimize.opt_a.merge_forward : 0.000031s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000052s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000107s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000089s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000032s : 0.00% optimize.opt_a.meta_fg_expand : 0.000034s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000060s : 0.00% optimize.opt_a.a_after_grad : 0.000077s : 0.00% optimize.opt_a.renormalize : 0.300170s : 12.27% optimize.opt_a.add_forward_monad_depend : 0.000027s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000101s : 0.00% optimize.opt_a.cse : 0.000397s : 0.02% optimize.opt_a.a_3 : 0.000343s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000038s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.001024s : 0.04% optimize.convert_after_rewriter : 0.000033s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000973s : 0.04% optimize.opt_b.b_1 : 0.000604s : 0.02% optimize.opt_b.b_2 : 0.000030s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000125s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000045s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000046s : 0.00% optimize.loop_unroll : 0.000573s : 0.02% optimize.opt_after_cconv.c_1 : 0.000119s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.cse : 0.000228s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000140s : 0.01% optimize.tuple_transform.d_1 : 0.000243s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000173s : 0.01% optimize.cse_after_recomputation.cse : 0.000075s : 0.00% optimize.environ_conv : 0.000024s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000027s : 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 : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000048s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000011s : 0.00% optimize.overlap_grad_flash_sp : 0.000058s : 0.00% 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 : 0.000287s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000038s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000075s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000194s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000063s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000061s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000788s : 0.03% validate : 0.000100s : 0.00% Time group info: ------[substitution.] 0.190191 665 0.03% : 0.000063s : 7: substitution.arithmetic_simplify 0.01% : 0.000010s : 7: substitution.depend_value_elim 0.02% : 0.000029s : 17: substitution.elim_not_effective 0.01% : 0.000024s : 20: substitution.float_tuple_getitem_switch 0.01% : 0.000028s : 13: substitution.fold_const_symbol 0.01% : 0.000017s : 19: substitution.graph_param_transform 99.31% : 0.188876s : 100: substitution.inline 0.01% : 0.000017s : 35: substitution.j_node_and_user_rematch 0.02% : 0.000033s : 7: substitution.less_batch_normalization 0.04% : 0.000079s : 3: substitution.list_to_tuple_eliminator_ 0.01% : 0.000028s : 15: substitution.minmaximum_grad 0.04% : 0.000068s : 6: substitution.opt_reshape 0.01% : 0.000025s : 35: substitution.remove_not_recompute_node 0.00% : 0.000008s : 2: substitution.replace_old_param 0.05% : 0.000089s : 29: substitution.reshape_eliminate 0.03% : 0.000060s : 21: substitution.switch_simplify 0.09% : 0.000167s : 60: substitution.tuple_list_convert_item_index_to_positive 0.04% : 0.000081s : 60: substitution.tuple_list_get_item_const_eliminator 0.06% : 0.000121s : 60: substitution.tuple_list_get_item_depend_reorder 0.13% : 0.000254s : 89: substitution.tuple_list_get_item_eliminator 0.06% : 0.000113s : 60: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.932023 2 93.23% : 1.801287s : 1: type_inference.infer 6.77% : 0.130737s : 1: type_inference.specialize ------[replace.] 0.002145 148 3.11% : 0.000067s : 7: replace.depend_value_elim 68.78% : 0.001475s : 100: replace.inline 2.65% : 0.000057s : 3: replace.list_to_tuple_eliminator_ 3.37% : 0.000072s : 3: replace.opt_reshape 16.10% : 0.000345s : 21: replace.switch_simplify 5.98% : 0.000128s : 14: replace.tuple_list_get_item_eliminator ------[match.] 0.189037 148 0.00% : 0.000006s : 7: match.depend_value_elim 99.88% : 0.188812s : 100: match.inline 0.04% : 0.000075s : 3: match.list_to_tuple_eliminator_ 0.03% : 0.000060s : 3: match.opt_reshape 0.03% : 0.000048s : 21: match.switch_simplify 0.02% : 0.000036s : 14: match.tuple_list_get_item_eliminator ------[predicate.] 0.002200 12232 1.10% : 0.000024s : 167: predicate.accumulaten_eliminater 0.25% : 0.000006s : 18: predicate.ad_related_special_op_eliminate 0.44% : 0.000010s : 66: predicate.addn_check_dump 1.16% : 0.000025s : 167: predicate.addn_zero_filter 1.09% : 0.000024s : 167: predicate.adjust_all_reduce_mul_add 2.16% : 0.000047s : 233: predicate.arithmetic_simplify 1.25% : 0.000027s : 167: predicate.cast_eliminate 0.28% : 0.000006s : 38: predicate.check_bprop_eliminate 0.42% : 0.000009s : 66: predicate.compare_switch_simplify 0.07% : 0.000002s : 19: predicate.const_output_eliminate 0.52% : 0.000011s : 70: predicate.depend_value_elim 1.17% : 0.000026s : 167: predicate.dict_get_item_const_eliminator 1.36% : 0.000030s : 167: predicate.dict_get_item_eliminator 1.16% : 0.000026s : 167: predicate.dict_set_item_eliminator 0.32% : 0.000007s : 37: predicate.dumpgradient_eliminate 0.08% : 0.000002s : 19: predicate.elim_not_effective 0.23% : 0.000005s : 19: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000026s : 186: predicate.environ_add_const_eliminate 1.23% : 0.000027s : 186: predicate.environ_get_add_eliminate 1.28% : 0.000028s : 186: predicate.environ_get_depend_swap 1.74% : 0.000038s : 252: predicate.environ_get_eliminate 1.26% : 0.000028s : 186: predicate.environ_get_set_eliminate 1.90% : 0.000042s : 284: predicate.exchange_switch_depend_value 2.78% : 0.000061s : 284: predicate.float_depend_g_call 0.44% : 0.000010s : 66: predicate.float_environ_get_switch 0.64% : 0.000014s : 85: predicate.float_tuple_getitem_switch 0.07% : 0.000001s : 18: predicate.fold_const_symbol 0.30% : 0.000007s : 39: predicate.get_grad_eliminate 0.08% : 0.000002s : 19: predicate.graph_param_transform 0.43% : 0.000009s : 66: predicate.incorporate_call 0.43% : 0.000009s : 66: predicate.incorporate_call_switch 5.77% : 0.000127s : 594: predicate.inline 0.38% : 0.000008s : 39: predicate.inline_without_move 0.13% : 0.000003s : 39: predicate.j_node_and_user_rematch 0.39% : 0.000009s : 39: predicate.less_batch_normalization 1.65% : 0.000036s : 222: predicate.list_to_tuple_eliminator_ 2.49% : 0.000055s : 389: predicate.load_eliminater 0.32% : 0.000007s : 19: predicate.loop_unroll_after_grad 3.16% : 0.000070s : 290: predicate.loop_unroll_before_grad 1.52% : 0.000033s : 205: predicate.make_slice_get_slice_eliminator 0.45% : 0.000010s : 66: predicate.merge_addn 0.28% : 0.000006s : 38: predicate.micro_step_allgather_replace 0.26% : 0.000006s : 38: predicate.mini_step_allgather_replace 3.03% : 0.000067s : 167: predicate.minmaximum_grad 0.40% : 0.000009s : 19: predicate.mutable_eliminate 0.25% : 0.000005s : 24: predicate.opt_reshape 0.15% : 0.000003s : 19: predicate.parallel_virtual_node 3.67% : 0.000081s : 284: predicate.partial_defer_inline 1.54% : 0.000034s : 203: predicate.partial_eliminate 1.08% : 0.000024s : 167: predicate.print_const_string_wrapper 0.43% : 0.000009s : 59: predicate.reduce_all_const_elim 1.53% : 0.000034s : 167: predicate.reduce_eliminate 2.65% : 0.000058s : 389: predicate.redundant_stop_gradient_eliminater 0.14% : 0.000003s : 39: predicate.remove_not_recompute_node 1.08% : 0.000024s : 222: predicate.replace_applicator 0.18% : 0.000004s : 39: predicate.replace_old_param 0.09% : 0.000002s : 19: predicate.reset_defer_inline 1.37% : 0.000030s : 167: predicate.reshape_eliminate 0.26% : 0.000006s : 38: predicate.row_tensor_add_zeros_like 0.17% : 0.000004s : 19: predicate.row_tensor_eliminate 0.35% : 0.000008s : 38: predicate.same_eliminate 0.18% : 0.000004s : 46: predicate.set_cell_output_no_recompute 0.47% : 0.000010s : 39: predicate.shard_identity_eliminate 0.26% : 0.000006s : 37: predicate.special_op_eliminate 0.53% : 0.000012s : 66: predicate.specialize_transform 0.39% : 0.000009s : 38: predicate.split_environ_get_set_with_tuple_value 0.34% : 0.000007s : 39: predicate.stack_unstack_eliminate 0.14% : 0.000003s : 19: predicate.switch_call_monad_eliminater 2.14% : 0.000047s : 284: predicate.switch_defer_inline 2.35% : 0.000052s : 322: predicate.switch_layer_defer_inline 7.05% : 0.000155s : 701: predicate.switch_simplify 1.15% : 0.000025s : 167: predicate.tile_eliminate 1.18% : 0.000026s : 167: predicate.transpose_eliminate 3.84% : 0.000085s : 205: predicate.tuple_list_convert_item_index_to_positive 1.79% : 0.000039s : 205: predicate.tuple_list_get_item_const_eliminator 1.57% : 0.000034s : 205: predicate.tuple_list_get_item_depend_reorder 2.94% : 0.000065s : 285: predicate.tuple_list_get_item_eliminator 1.71% : 0.000038s : 205: predicate.tuple_list_get_set_item_eliminator 2.01% : 0.000044s : 271: predicate.tuple_list_set_item_eliminator 1.49% : 0.000033s : 219: predicate.tuple_to_list_eliminator_ 2.45% : 0.000054s : 389: predicate.updatestate_pure_node_eliminater 2.99% : 0.000066s : 455: predicate.updatestate_useless_node_eliminater 0.15% : 0.000003s : 19: predicate.value_based_eliminate 0.31% : 0.000007s : 39: predicate.virtual_dataset_eliminate 0.29% : 0.000006s : 39: predicate.virtual_output_eliminate 0.12% : 0.000003s : 18: predicate.virtual_view_grad_eliminate 0.18% : 0.000004s : 19: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.128103 137 5.49% : 0.007039s : 45: func_graph_cloner_run.FuncGraphClonerGraph 1.60% : 0.002055s : 17: func_graph_cloner_run.FuncGraphClonerNode 92.90% : 0.119009s : 75: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.475260 209 0.00% : 0.000005s : 1: ForceFp32Comm 0.18% : 0.006145s : 1: add_attr 0.18% : 0.006122s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000178s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000692s : 1: auto_monad 0.00% : 0.000066s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.03% : 0.000955s : 1: bootstrap 0.00% : 0.000050s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000051s : 1: control_data_broadcast_order 0.00% : 0.000039s : 1: convert_after_rewriter 0.00% : 0.000094s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000027s : 1: environ_conv 0.01% : 0.000279s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000086s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000583s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.000984s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.00% : 0.000040s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000047s : 1: opt.transform.mutable_eliminate 5.82% : 0.202172s : 95: opt.transform.opt_a 0.00% : 0.000118s : 1: opt.transform.opt_after_cconv 0.00% : 0.000077s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000594s : 28: opt.transform.opt_b 0.01% : 0.000263s : 2: opt.transform.opt_trans_graph 0.01% : 0.000362s : 4: opt.transform.symbol_engine_opt 14.52% : 0.504543s : 1: opt_a 0.01% : 0.000454s : 1: opt_after_cconv 0.02% : 0.000799s : 1: opt_after_jit_grad 0.02% : 0.000862s : 1: opt_b 14.73% : 0.511772s : 1: optimize 0.00% : 0.000049s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000062s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000014s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000338s : 1: pre_auto_parallel 0.01% : 0.000307s : 1: py_interpret_to_execute 0.00% : 0.000042s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000145s : 1: remove_dup_value 8.49% : 0.294950s : 1: renormalize.infer 0.15% : 0.005197s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.001037s : 1: rewriter_after_opt_a 0.03% : 0.000885s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000031s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000741s : 1: symbol_engine_optimizer 0.01% : 0.000304s : 1: tuple_transform 55.61% : 1.932449s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[False-True-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[False-True-bfloat16--1-shape0],max_mem:116.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:38:41.878.875 [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 = 3.11932, [21] [bootstrap]: 0.00075881 [type_inference]: 2.26053 [event_method]: 0.00021316 [auto_monad]: 0.00061214 [graph_reusing]: 7.376e-05 [inline]: 3.71001e-06 [add_attr]: 0.00523056, [1] [add_attr_with_inline]: 0.00521452, [1] [Cycle 1]: 0.00033333, [2] [tag_attr]: 0.00023886 [meta_addattr_fg_expand]: 4.511e-05 [parallel-infer-symbol]: 5.76e-06 [pre_auto_parallel]: 0.00022726 [insert-virtual-dataset]: 4.11001e-06 [parallel-infer-symbol-second]: 1.07e-06 [dataset_repeat_opt]: 2.71999e-06 [pipeline_split]: 3.18e-06 [optimize]: 0.850567, [53] [py_interpret_to_execute]: 0.0002575 [rewriter_before_opt_a]: 0.0007631 [opt_a]: 0.843526, [2] [Cycle 1]: 0.841289, [45] [expand_dump_flag]: 1.576e-05 [switch_simplify]: 0.127903 [loop_unroll]: 0.00059774 [a_1]: 0.350878 [with_stream_mark]: 0.00013526 [recompute_prepare]: 4.771e-05 [updatestate_depend_eliminate]: 2.694e-05 [updatestate_assign_eliminate]: 1.765e-05 [updatestate_loads_eliminate]: 1.706e-05 [parameter_eliminate]: 3.60998e-06 [a_2]: 0.00095369 [accelerated_algorithm]: 6.341e-05 [shard]: 2.44001e-06 [meta_shard_fg_expand]: 3.297e-05 [shard_inline]: 2.571e-05 [merge_send_recv]: 2.211e-05 [auto_parallel]: 2.302e-05 [parallel]: 3.523e-05 [flash_sp]: 1.684e-05 [merge_comm]: 1.522e-05 [allreduce_fusion]: 1.477e-05 [matmul_add_comm_reduction]: 2.289e-05 [allreduce_slice_to_reducescatter]: 9.89996e-07 [virtual_shard_identity]: 2.893e-05 [virtual_dataset]: 2.464e-05 [get_grad_eliminate_]: 2.335e-05 [virtual_output]: 2.39e-05 [merge_forward]: 1.533e-05 [cell_reuse_recompute_pass]: 2.14999e-06 [offload_activation]: 2.584e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.063e-05 [merge_recompute_call_nodes]: 1.50001e-06 [before_grad]: 4.482e-05 [set_forward_comm_id_for_comm_node_pass]: 1.553e-05 [meta_fg_expand]: 2.05e-05 [flash_sp_send_recv_attached]: 5.12e-06 [receive_attached]: 2.41e-06 [after_resolve]: 2.909e-05 [a_after_grad]: 3.802e-05 [renormalize]: 0.358839 [add_forward_monad_depend]: 2.31e-05 [auto_monad_grad]: 3.56001e-06 [auto_monad_eliminator]: 7.379e-05 [cse]: 0.00042253 [a_3]: 0.00018815 [Cycle 2]: 0.00221823, [45] [expand_dump_flag]: 3.25998e-06 [switch_simplify]: 2.863e-05 [loop_unroll]: 2.507e-05 [a_1]: 0.00072383 [with_stream_mark]: 3.453e-05 [recompute_prepare]: 2.362e-05 [updatestate_depend_eliminate]: 1.582e-05 [updatestate_assign_eliminate]: 1.193e-05 [updatestate_loads_eliminate]: 1.185e-05 [parameter_eliminate]: 2.75002e-06 [a_2]: 0.00033705 [accelerated_algorithm]: 3.143e-05 [shard]: 2.41998e-06 [meta_shard_fg_expand]: 8.35999e-06 [shard_inline]: 2.196e-05 [merge_send_recv]: 2.038e-05 [auto_parallel]: 2.126e-05 [parallel]: 1e-05 [flash_sp]: 5.35001e-06 [merge_comm]: 1.368e-05 [allreduce_fusion]: 1.323e-05 [matmul_add_comm_reduction]: 2.334e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 2.561e-05 [virtual_dataset]: 2.144e-05 [get_grad_eliminate_]: 2.16e-05 [virtual_output]: 2.133e-05 [merge_forward]: 1.336e-05 [cell_reuse_recompute_pass]: 3.21999e-06 [offload_activation]: 2.283e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.525e-05 [merge_recompute_call_nodes]: 1.99999e-06 [before_grad]: 4.011e-05 [set_forward_comm_id_for_comm_node_pass]: 1.449e-05 [meta_fg_expand]: 1.068e-05 [flash_sp_send_recv_attached]: 1.49e-06 [receive_attached]: 2.59001e-06 [after_resolve]: 2.726e-05 [a_after_grad]: 3.467e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.17002e-06 [auto_monad_grad]: 3.06001e-06 [auto_monad_eliminator]: 3.77e-05 [cse]: 9.049e-05 [a_3]: 0.00014996 [py_interpret_to_execute_after_opt_a]: 3.929e-05 [slice_cell_reuse_recomputed_activation]: 2.55002e-06 [rewriter_after_opt_a]: 0.00102831 [convert_after_rewriter]: 2.926e-05 [order_py_execute_after_rewriter]: 1.393e-05 [mutable_eliminate]: 0.00088374 [opt_b]: 0.00105369, [1] [Cycle 1]: 0.00104311, [7] [b_1]: 0.00079722 [b_2]: 2.869e-05 [updatestate_depend_eliminate]: 2.196e-05 [updatestate_assign_eliminate]: 1.221e-05 [updatestate_loads_eliminate]: 1.209e-05 [renormalize]: 4.39992e-07 [cse]: 0.00011961 [optimize_parallel_all_gather_comm]: 4.605e-05 [overlap_param_gather]: 2.47001e-06 [cconv]: 4.44e-05 [loop_unroll]: 0.00059273 [opt_after_cconv]: 0.00028872, [1] [Cycle 1]: 0.00028209, [7] [c_1]: 0.00011762 [parameter_eliminate]: 5.61e-06 [updatestate_depend_eliminate]: 1.702e-05 [updatestate_assign_eliminate]: 1.086e-05 [updatestate_loads_eliminate]: 1.15e-05 [cse]: 8.251e-05 [renormalize]: 9.39996e-07 [remove_dup_value]: 0.0001354 [tuple_transform]: 0.00032036, [1] [Cycle 1]: 0.00031273, [4] [d_1]: 0.00026167 [none_parameter_eliminate]: 2.69001e-06 [renormalize]: 3.59985e-07 [switch_simplify]: 2.401e-05 [partial_unused_args_eliminate]: 1.97001e-06 [add_recomputation]: 0.00016376 [cse_after_recomputation]: 6.955e-05, [1] [Cycle 1]: 6.28e-05, [1] [cse]: 5.666e-05 [environ_conv]: 2.312e-05 [swap_dp_allreduce_reducescatter]: 1.905e-05 [bias_add_comm_swap]: 3.31001e-06 [label_micro_interleaved_index]: 6.955e-05 [label_fine_grained_interleaved_index]: 2.79001e-06 [merge_cast_opt]: 1.35999e-06 [slice_recompute_activation]: 2.23002e-06 [micro_interleaved_order_control]: 2.76e-06 [assign_add_opt]: 1.22e-06 [ForceFp32Comm]: 8.39995e-07 [remove_cast_before_assign_add]: 1.07e-06 [full_micro_interleaved_order_control]: 2.13002e-06 [reorder_send_recv_between_fp_bp]: 2.59001e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.30001e-06 [interleave_split_concat_branches]: 1.32e-06 [interleave_parallel_branches]: 1.09998e-06 [overlap_opt_shard_in_pipeline]: 1.57001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.83002e-06 [control_data_broadcast_order]: 7.301e-05 [grouped_pairwise_exchange_alltoall]: 1.54998e-06 [offloading_packed_experts]: 1.332e-05 [overlap_recompute_and_grad_model_parallel]: 1.116e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.32e-06 [overlap_recompute_allgather_and_fa_grad]: 1.76e-06 [overlap_recompute_comm]: 2.83003e-06 [overlap_grad_ring_attention]: 1.054e-05 [overlap_grad_flash_sp]: 5.809e-05 [begin_end_overlap_inline]: 4.89992e-07 [split_matmul_comm_elemetwise]: 2.28998e-06 [split_layernorm_comm]: 1.66e-06 [handle_group_info]: 9.80013e-07 [symbol_engine_optimizer]: 0.000672, [1] [Cycle 1]: 0.00066586, [6] [build]: 0.00028506 [elim_shapecalc]: 3.622e-05 [elim_not_effective]: 5.592e-05 [opt_reshape]: 0.00017845 [fold_const_symbol]: 5.779e-05 [renormalize]: 5.19998e-07 [detach_backward]: 3.24001e-06 [pipeline_parallel_scheduler]: 2.14e-06 [auto_monad_reorder]: 6.082e-05 [get_jit_bprop_graph]: 2.51e-06 [rewriter_after_jit_bprop_graph]: 6.76999e-06 [opt_after_jit_grad]: 0.00066291 [validate]: 9.742e-05 Sums bootstrap : 0.000759s : 0.02% type_inference : 2.260529s : 72.62% event_method : 0.000213s : 0.01% auto_monad : 0.000612s : 0.02% graph_reusing : 0.000074s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000239s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000045s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000227s : 0.01% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000257s : 0.01% optimize.rewriter_before_opt_a : 0.000763s : 0.02% optimize.opt_a.expand_dump_flag : 0.000019s : 0.00% optimize.opt_a.switch_simplify : 0.127931s : 4.11% optimize.opt_a.loop_unroll : 0.000623s : 0.02% optimize.opt_a.a_1 : 0.351601s : 11.30% optimize.opt_a.with_stream_mark : 0.000170s : 0.01% optimize.opt_a.recompute_prepare : 0.000071s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000043s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000030s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000029s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001291s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000095s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000041s : 0.00% optimize.opt_a.shard_inline : 0.000048s : 0.00% optimize.opt_a.merge_send_recv : 0.000042s : 0.00% optimize.opt_a.auto_parallel : 0.000044s : 0.00% optimize.opt_a.parallel : 0.000045s : 0.00% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000029s : 0.00% optimize.opt_a.allreduce_fusion : 0.000028s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000046s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000055s : 0.00% optimize.opt_a.virtual_dataset : 0.000046s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000045s : 0.00% optimize.opt_a.virtual_output : 0.000045s : 0.00% optimize.opt_a.merge_forward : 0.000029s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000049s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000096s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000085s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000030s : 0.00% optimize.opt_a.meta_fg_expand : 0.000031s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000056s : 0.00% optimize.opt_a.a_after_grad : 0.000073s : 0.00% optimize.opt_a.renormalize : 0.358839s : 11.53% optimize.opt_a.add_forward_monad_depend : 0.000026s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000111s : 0.00% optimize.opt_a.cse : 0.000513s : 0.02% optimize.opt_a.a_3 : 0.000338s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000039s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.001028s : 0.03% optimize.convert_after_rewriter : 0.000029s : 0.00% optimize.order_py_execute_after_rewriter : 0.000014s : 0.00% optimize.mutable_eliminate : 0.000884s : 0.03% optimize.opt_b.b_1 : 0.000797s : 0.03% optimize.opt_b.b_2 : 0.000029s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000120s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000046s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.000593s : 0.02% optimize.opt_after_cconv.c_1 : 0.000118s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.cse : 0.000083s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000135s : 0.00% optimize.tuple_transform.d_1 : 0.000262s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000024s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000164s : 0.01% optimize.cse_after_recomputation.cse : 0.000057s : 0.00% optimize.environ_conv : 0.000023s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000019s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000070s : 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 : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000073s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000011s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000011s : 0.00% optimize.overlap_grad_flash_sp : 0.000058s : 0.00% optimize.begin_end_overlap_inline : 0.000000s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000285s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000036s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000056s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000178s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000058s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000061s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000663s : 0.02% validate : 0.000097s : 0.00% Time group info: ------[substitution.] 0.006710 665 0.97% : 0.000065s : 7: substitution.arithmetic_simplify 0.13% : 0.000009s : 7: substitution.depend_value_elim 0.24% : 0.000016s : 17: substitution.elim_not_effective 0.34% : 0.000023s : 20: substitution.float_tuple_getitem_switch 0.39% : 0.000026s : 13: substitution.fold_const_symbol 0.25% : 0.000017s : 19: substitution.graph_param_transform 78.74% : 0.005284s : 100: substitution.inline 0.25% : 0.000017s : 35: substitution.j_node_and_user_rematch 0.49% : 0.000033s : 7: substitution.less_batch_normalization 1.27% : 0.000085s : 3: substitution.list_to_tuple_eliminator_ 0.46% : 0.000031s : 15: substitution.minmaximum_grad 0.95% : 0.000064s : 6: substitution.opt_reshape 0.37% : 0.000025s : 35: substitution.remove_not_recompute_node 0.10% : 0.000007s : 2: substitution.replace_old_param 1.40% : 0.000094s : 29: substitution.reshape_eliminate 1.12% : 0.000075s : 21: substitution.switch_simplify 2.71% : 0.000182s : 60: substitution.tuple_list_convert_item_index_to_positive 1.40% : 0.000094s : 60: substitution.tuple_list_get_item_const_eliminator 2.06% : 0.000138s : 60: substitution.tuple_list_get_item_depend_reorder 4.33% : 0.000291s : 89: substitution.tuple_list_get_item_eliminator 2.02% : 0.000135s : 60: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.260189 2 88.73% : 2.005403s : 1: type_inference.infer 11.27% : 0.254786s : 1: type_inference.specialize ------[replace.] 0.002337 148 2.91% : 0.000068s : 7: replace.depend_value_elim 67.09% : 0.001568s : 100: replace.inline 2.88% : 0.000067s : 3: replace.list_to_tuple_eliminator_ 2.73% : 0.000064s : 3: replace.opt_reshape 17.33% : 0.000405s : 21: replace.switch_simplify 7.06% : 0.000165s : 14: replace.tuple_list_get_item_eliminator ------[match.] 0.005460 148 0.11% : 0.000006s : 7: match.depend_value_elim 95.59% : 0.005219s : 100: match.inline 1.49% : 0.000081s : 3: match.list_to_tuple_eliminator_ 1.06% : 0.000058s : 3: match.opt_reshape 1.09% : 0.000059s : 21: match.switch_simplify 0.67% : 0.000036s : 14: match.tuple_list_get_item_eliminator ------[predicate.] 0.002352 12232 1.04% : 0.000025s : 167: predicate.accumulaten_eliminater 0.22% : 0.000005s : 18: predicate.ad_related_special_op_eliminate 0.40% : 0.000009s : 66: predicate.addn_check_dump 1.03% : 0.000024s : 167: predicate.addn_zero_filter 1.03% : 0.000024s : 167: predicate.adjust_all_reduce_mul_add 2.03% : 0.000048s : 233: predicate.arithmetic_simplify 1.06% : 0.000025s : 167: predicate.cast_eliminate 0.24% : 0.000006s : 38: predicate.check_bprop_eliminate 0.44% : 0.000010s : 66: predicate.compare_switch_simplify 0.06% : 0.000001s : 19: predicate.const_output_eliminate 0.46% : 0.000011s : 70: predicate.depend_value_elim 1.10% : 0.000026s : 167: predicate.dict_get_item_const_eliminator 1.25% : 0.000029s : 167: predicate.dict_get_item_eliminator 1.17% : 0.000027s : 167: predicate.dict_set_item_eliminator 0.28% : 0.000007s : 37: predicate.dumpgradient_eliminate 0.07% : 0.000002s : 19: predicate.elim_not_effective 0.16% : 0.000004s : 19: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000027s : 186: predicate.environ_add_const_eliminate 1.14% : 0.000027s : 186: predicate.environ_get_add_eliminate 1.11% : 0.000026s : 186: predicate.environ_get_depend_swap 1.57% : 0.000037s : 252: predicate.environ_get_eliminate 1.15% : 0.000027s : 186: predicate.environ_get_set_eliminate 1.81% : 0.000043s : 284: predicate.exchange_switch_depend_value 2.66% : 0.000063s : 284: predicate.float_depend_g_call 0.41% : 0.000010s : 66: predicate.float_environ_get_switch 0.57% : 0.000014s : 85: predicate.float_tuple_getitem_switch 0.06% : 0.000001s : 18: predicate.fold_const_symbol 0.26% : 0.000006s : 39: predicate.get_grad_eliminate 0.08% : 0.000002s : 19: predicate.graph_param_transform 0.43% : 0.000010s : 66: predicate.incorporate_call 0.37% : 0.000009s : 66: predicate.incorporate_call_switch 5.40% : 0.000127s : 594: predicate.inline 0.33% : 0.000008s : 39: predicate.inline_without_move 0.11% : 0.000003s : 39: predicate.j_node_and_user_rematch 0.35% : 0.000008s : 39: predicate.less_batch_normalization 1.48% : 0.000035s : 222: predicate.list_to_tuple_eliminator_ 2.31% : 0.000054s : 389: predicate.load_eliminater 0.27% : 0.000006s : 19: predicate.loop_unroll_after_grad 5.12% : 0.000120s : 290: predicate.loop_unroll_before_grad 1.40% : 0.000033s : 205: predicate.make_slice_get_slice_eliminator 0.45% : 0.000010s : 66: predicate.merge_addn 0.24% : 0.000006s : 38: predicate.micro_step_allgather_replace 0.24% : 0.000006s : 38: predicate.mini_step_allgather_replace 1.03% : 0.000024s : 167: predicate.minmaximum_grad 0.38% : 0.000009s : 19: predicate.mutable_eliminate 0.20% : 0.000005s : 24: predicate.opt_reshape 0.14% : 0.000003s : 19: predicate.parallel_virtual_node 3.76% : 0.000088s : 284: predicate.partial_defer_inline 1.36% : 0.000032s : 203: predicate.partial_eliminate 1.03% : 0.000024s : 167: predicate.print_const_string_wrapper 0.37% : 0.000009s : 59: predicate.reduce_all_const_elim 1.45% : 0.000034s : 167: predicate.reduce_eliminate 2.41% : 0.000057s : 389: predicate.redundant_stop_gradient_eliminater 0.12% : 0.000003s : 39: predicate.remove_not_recompute_node 0.98% : 0.000023s : 222: predicate.replace_applicator 0.14% : 0.000003s : 39: predicate.replace_old_param 0.07% : 0.000002s : 19: predicate.reset_defer_inline 1.20% : 0.000028s : 167: predicate.reshape_eliminate 0.23% : 0.000005s : 38: predicate.row_tensor_add_zeros_like 0.14% : 0.000003s : 19: predicate.row_tensor_eliminate 0.35% : 0.000008s : 38: predicate.same_eliminate 0.16% : 0.000004s : 46: predicate.set_cell_output_no_recompute 0.30% : 0.000007s : 39: predicate.shard_identity_eliminate 0.24% : 0.000006s : 37: predicate.special_op_eliminate 0.48% : 0.000011s : 66: predicate.specialize_transform 0.29% : 0.000007s : 38: predicate.split_environ_get_set_with_tuple_value 0.29% : 0.000007s : 39: predicate.stack_unstack_eliminate 0.12% : 0.000003s : 19: predicate.switch_call_monad_eliminater 2.25% : 0.000053s : 284: predicate.switch_defer_inline 2.15% : 0.000051s : 322: predicate.switch_layer_defer_inline 6.90% : 0.000162s : 701: predicate.switch_simplify 1.02% : 0.000024s : 167: predicate.tile_eliminate 1.04% : 0.000024s : 167: predicate.transpose_eliminate 1.60% : 0.000038s : 205: predicate.tuple_list_convert_item_index_to_positive 1.56% : 0.000037s : 205: predicate.tuple_list_get_item_const_eliminator 9.62% : 0.000226s : 205: predicate.tuple_list_get_item_depend_reorder 2.77% : 0.000065s : 285: predicate.tuple_list_get_item_eliminator 1.54% : 0.000036s : 205: predicate.tuple_list_get_set_item_eliminator 2.23% : 0.000053s : 271: predicate.tuple_list_set_item_eliminator 1.56% : 0.000037s : 219: predicate.tuple_to_list_eliminator_ 2.32% : 0.000055s : 389: predicate.updatestate_pure_node_eliminater 2.82% : 0.000066s : 455: predicate.updatestate_useless_node_eliminater 0.12% : 0.000003s : 19: predicate.value_based_eliminate 0.25% : 0.000006s : 39: predicate.virtual_dataset_eliminate 0.26% : 0.000006s : 39: predicate.virtual_output_eliminate 0.12% : 0.000003s : 18: predicate.virtual_view_grad_eliminate 0.15% : 0.000003s : 19: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.746864 137 99.06% : 0.739863s : 45: func_graph_cloner_run.FuncGraphClonerGraph 0.27% : 0.002003s : 17: func_graph_cloner_run.FuncGraphClonerNode 0.67% : 0.004998s : 75: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.817706 209 0.00% : 0.000003s : 1: ForceFp32Comm 0.11% : 0.005237s : 1: add_attr 0.11% : 0.005219s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000168s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000626s : 1: auto_monad 0.00% : 0.000065s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000795s : 1: bootstrap 0.00% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000077s : 1: control_data_broadcast_order 0.00% : 0.000035s : 1: convert_after_rewriter 0.00% : 0.000072s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000026s : 1: environ_conv 0.00% : 0.000226s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000081s : 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% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000073s : 1: label_micro_interleaved_index 0.01% : 0.000603s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000896s : 1: mutable_eliminate 0.00% : 0.000016s : 1: offloading_packed_experts 0.00% : 0.000037s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000049s : 1: opt.transform.mutable_eliminate 10.01% : 0.482345s : 95: opt.transform.opt_a 0.00% : 0.000116s : 1: opt.transform.opt_after_cconv 0.00% : 0.000075s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000785s : 28: opt.transform.opt_b 0.01% : 0.000282s : 2: opt.transform.opt_trans_graph 0.01% : 0.000322s : 4: opt.transform.symbol_engine_opt 17.51% : 0.843531s : 1: opt_a 0.01% : 0.000292s : 1: opt_after_cconv 0.01% : 0.000674s : 1: opt_after_jit_grad 0.02% : 0.001079s : 1: opt_b 17.66% : 0.850573s : 1: optimize 0.00% : 0.000051s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000062s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 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% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000235s : 1: pre_auto_parallel 0.01% : 0.000265s : 1: py_interpret_to_execute 0.00% : 0.000044s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000141s : 1: remove_dup_value 0.10% : 0.004699s : 1: renormalize.infer 7.35% : 0.354120s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.001042s : 1: rewriter_after_opt_a 0.02% : 0.000773s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000022s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000676s : 1: symbol_engine_optimizer 0.01% : 0.000323s : 1: tuple_transform 46.92% : 2.260582s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[False-True-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[False-True-bfloat16--1-shape1],max_mem:120.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:38:57.625.170 [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 = 2.6213, [21] [bootstrap]: 0.00072001 [type_inference]: 1.89963 [event_method]: 0.00026276 [auto_monad]: 0.00086384 [graph_reusing]: 0.0001009 [inline]: 3.03e-06 [add_attr]: 0.248466, [1] [add_attr_with_inline]: 0.248443, [1] [Cycle 1]: 0.00033835, [2] [tag_attr]: 0.00022795 [meta_addattr_fg_expand]: 5.108e-05 [parallel-infer-symbol]: 5.77001e-06 [pre_auto_parallel]: 0.00027662 [insert-virtual-dataset]: 4.56002e-06 [parallel-infer-symbol-second]: 1.15001e-06 [dataset_repeat_opt]: 2.51998e-06 [pipeline_split]: 3.40003e-06 [optimize]: 0.469587, [53] [py_interpret_to_execute]: 0.00033053 [rewriter_before_opt_a]: 0.0008542 [opt_a]: 0.256592, [2] [Cycle 1]: 0.253842, [45] [expand_dump_flag]: 3.446e-05 [switch_simplify]: 0.00082554 [loop_unroll]: 0.00027209 [a_1]: 0.0144557 [with_stream_mark]: 0.00016083 [recompute_prepare]: 5.227e-05 [updatestate_depend_eliminate]: 2.983e-05 [updatestate_assign_eliminate]: 1.692e-05 [updatestate_loads_eliminate]: 1.652e-05 [parameter_eliminate]: 3.22002e-06 [a_2]: 0.222677 [accelerated_algorithm]: 0.00016132 [shard]: 3.5e-06 [meta_shard_fg_expand]: 4.145e-05 [shard_inline]: 2.91e-05 [merge_send_recv]: 2.838e-05 [auto_parallel]: 2.441e-05 [parallel]: 3.757e-05 [flash_sp]: 1.918e-05 [merge_comm]: 1.57e-05 [allreduce_fusion]: 1.404e-05 [matmul_add_comm_reduction]: 2.339e-05 [allreduce_slice_to_reducescatter]: 1.19003e-06 [virtual_shard_identity]: 3.633e-05 [virtual_dataset]: 2.623e-05 [get_grad_eliminate_]: 2.427e-05 [virtual_output]: 2.374e-05 [merge_forward]: 1.396e-05 [cell_reuse_recompute_pass]: 4.08999e-06 [offload_activation]: 3.041e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.904e-05 [merge_recompute_call_nodes]: 2.12999e-06 [before_grad]: 4.97e-05 [set_forward_comm_id_for_comm_node_pass]: 1.633e-05 [meta_fg_expand]: 2.756e-05 [flash_sp_send_recv_attached]: 6.38998e-06 [receive_attached]: 2.64999e-06 [after_resolve]: 3.338e-05 [a_after_grad]: 4.077e-05 [renormalize]: 0.0133933 [add_forward_monad_depend]: 2.175e-05 [auto_monad_grad]: 3.66001e-06 [auto_monad_eliminator]: 7.435e-05 [cse]: 0.00027717 [a_3]: 0.0001897 [Cycle 2]: 0.00273184, [45] [expand_dump_flag]: 2.44001e-06 [switch_simplify]: 2.639e-05 [loop_unroll]: 2.412e-05 [a_1]: 0.00078577 [with_stream_mark]: 3.39e-05 [recompute_prepare]: 2.523e-05 [updatestate_depend_eliminate]: 3.261e-05 [updatestate_assign_eliminate]: 1.319e-05 [updatestate_loads_eliminate]: 1.198e-05 [parameter_eliminate]: 2.79001e-06 [a_2]: 0.00035412 [accelerated_algorithm]: 3.546e-05 [shard]: 2.27999e-06 [meta_shard_fg_expand]: 1.063e-05 [shard_inline]: 2.232e-05 [merge_send_recv]: 2.349e-05 [auto_parallel]: 2.071e-05 [parallel]: 1.214e-05 [flash_sp]: 6.34001e-06 [merge_comm]: 1.478e-05 [allreduce_fusion]: 1.342e-05 [matmul_add_comm_reduction]: 2.48e-05 [allreduce_slice_to_reducescatter]: 8.80013e-07 [virtual_shard_identity]: 2.69e-05 [virtual_dataset]: 2.232e-05 [get_grad_eliminate_]: 0.00033776 [virtual_output]: 2.813e-05 [merge_forward]: 1.493e-05 [cell_reuse_recompute_pass]: 3.97002e-06 [offload_activation]: 2.637e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.169e-05 [merge_recompute_call_nodes]: 2.06e-06 [before_grad]: 4.093e-05 [set_forward_comm_id_for_comm_node_pass]: 1.409e-05 [meta_fg_expand]: 1.2e-05 [flash_sp_send_recv_attached]: 1.92999e-06 [receive_attached]: 2.50002e-06 [after_resolve]: 2.704e-05 [a_after_grad]: 3.67e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 3.98001e-06 [auto_monad_grad]: 2.76e-06 [auto_monad_eliminator]: 3.953e-05 [cse]: 0.00010992 [a_3]: 0.000155 [py_interpret_to_execute_after_opt_a]: 3.993e-05 [slice_cell_reuse_recomputed_activation]: 2.54999e-06 [rewriter_after_opt_a]: 0.206192 [convert_after_rewriter]: 4.906e-05 [order_py_execute_after_rewriter]: 1.471e-05 [mutable_eliminate]: 0.00092983 [opt_b]: 0.00097217, [1] [Cycle 1]: 0.00096267, [7] [b_1]: 0.0006778 [b_2]: 3.024e-05 [updatestate_depend_eliminate]: 2.643e-05 [updatestate_assign_eliminate]: 1.278e-05 [updatestate_loads_eliminate]: 1.174e-05 [renormalize]: 5.3001e-07 [cse]: 0.00015211 [optimize_parallel_all_gather_comm]: 4.959e-05 [overlap_param_gather]: 2.06e-06 [cconv]: 4.386e-05 [loop_unroll]: 0.00081469 [opt_after_cconv]: 0.00035194, [1] [Cycle 1]: 0.00034303, [7] [c_1]: 0.00013227 [parameter_eliminate]: 7.42002e-06 [updatestate_depend_eliminate]: 2.504e-05 [updatestate_assign_eliminate]: 1.24e-05 [updatestate_loads_eliminate]: 1.122e-05 [cse]: 0.00010947 [renormalize]: 7.90023e-07 [remove_dup_value]: 0.00014842 [tuple_transform]: 0.0003176, [1] [Cycle 1]: 0.00030822, [4] [d_1]: 0.00025631 [none_parameter_eliminate]: 2.77002e-06 [renormalize]: 2.80008e-07 [switch_simplify]: 2.424e-05 [partial_unused_args_eliminate]: 2.53003e-06 [add_recomputation]: 0.00026187 [cse_after_recomputation]: 0.00012131, [1] [Cycle 1]: 8.192e-05, [1] [cse]: 7.097e-05 [environ_conv]: 2.745e-05 [swap_dp_allreduce_reducescatter]: 1.963e-05 [bias_add_comm_swap]: 3.51999e-06 [label_micro_interleaved_index]: 7.18998e-06 [label_fine_grained_interleaved_index]: 3.00998e-06 [merge_cast_opt]: 1.43002e-06 [slice_recompute_activation]: 2.29001e-06 [micro_interleaved_order_control]: 2.34001e-06 [assign_add_opt]: 1.44e-06 [ForceFp32Comm]: 1.22e-06 [remove_cast_before_assign_add]: 1.07998e-06 [full_micro_interleaved_order_control]: 2.32999e-06 [reorder_send_recv_between_fp_bp]: 2.76e-06 [comm_op_add_attrs]: 1.29e-06 [add_comm_op_reuse_tag]: 9.60019e-07 [interleave_split_concat_branches]: 1.30001e-06 [interleave_parallel_branches]: 1.09e-06 [overlap_opt_shard_in_pipeline]: 1.41998e-06 [overlap_opt_shard_grad_in_pipeline]: 2.19001e-06 [control_data_broadcast_order]: 9.899e-05 [grouped_pairwise_exchange_alltoall]: 2.034e-05 [offloading_packed_experts]: 1.948e-05 [overlap_recompute_and_grad_model_parallel]: 5.404e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.61998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 3.12002e-06 [overlap_grad_ring_attention]: 1.454e-05 [overlap_grad_flash_sp]: 7.776e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 1.96e-06 [split_layernorm_comm]: 1.69998e-06 [handle_group_info]: 8.99978e-07 [symbol_engine_optimizer]: 0.00072321, [1] [Cycle 1]: 0.00071433, [6] [build]: 0.00026605 [elim_shapecalc]: 4.678e-05 [elim_not_effective]: 5.841e-05 [opt_reshape]: 0.00022181 [fold_const_symbol]: 6.349e-05 [renormalize]: 5.90022e-07 [detach_backward]: 3.67998e-06 [pipeline_parallel_scheduler]: 1.68002e-06 [auto_monad_reorder]: 7.318e-05 [get_jit_bprop_graph]: 2.32001e-06 [rewriter_after_jit_bprop_graph]: 6.07999e-06 [opt_after_jit_grad]: 0.00089736 [validate]: 0.00010784 Sums bootstrap : 0.000720s : 0.03% type_inference : 1.899628s : 80.11% event_method : 0.000263s : 0.01% auto_monad : 0.000864s : 0.04% graph_reusing : 0.000101s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000228s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000051s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000277s : 0.01% insert-virtual-dataset : 0.000005s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000331s : 0.01% optimize.rewriter_before_opt_a : 0.000854s : 0.04% optimize.opt_a.expand_dump_flag : 0.000037s : 0.00% optimize.opt_a.switch_simplify : 0.000852s : 0.04% optimize.opt_a.loop_unroll : 0.000296s : 0.01% optimize.opt_a.a_1 : 0.015241s : 0.64% optimize.opt_a.with_stream_mark : 0.000195s : 0.01% optimize.opt_a.recompute_prepare : 0.000078s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000062s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000030s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000029s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.223031s : 9.41% optimize.opt_a.accelerated_algorithm : 0.000197s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000052s : 0.00% optimize.opt_a.shard_inline : 0.000051s : 0.00% optimize.opt_a.merge_send_recv : 0.000052s : 0.00% optimize.opt_a.auto_parallel : 0.000045s : 0.00% optimize.opt_a.parallel : 0.000050s : 0.00% optimize.opt_a.flash_sp : 0.000026s : 0.00% optimize.opt_a.merge_comm : 0.000030s : 0.00% optimize.opt_a.allreduce_fusion : 0.000027s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000048s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000063s : 0.00% optimize.opt_a.virtual_dataset : 0.000049s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000362s : 0.02% optimize.opt_a.virtual_output : 0.000052s : 0.00% optimize.opt_a.merge_forward : 0.000029s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000008s : 0.00% optimize.opt_a.offload_activation : 0.000057s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000111s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000091s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000030s : 0.00% optimize.opt_a.meta_fg_expand : 0.000040s : 0.00% 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 : 0.000060s : 0.00% optimize.opt_a.a_after_grad : 0.000077s : 0.00% optimize.opt_a.renormalize : 0.013393s : 0.56% optimize.opt_a.add_forward_monad_depend : 0.000026s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000114s : 0.00% optimize.opt_a.cse : 0.000387s : 0.02% optimize.opt_a.a_3 : 0.000345s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000040s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.206192s : 8.70% optimize.convert_after_rewriter : 0.000049s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000930s : 0.04% optimize.opt_b.b_1 : 0.000678s : 0.03% optimize.opt_b.b_2 : 0.000030s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000026s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000152s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000050s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.000815s : 0.03% optimize.opt_after_cconv.c_1 : 0.000132s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000025s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.cse : 0.000109s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000148s : 0.01% optimize.tuple_transform.d_1 : 0.000256s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000024s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000262s : 0.01% optimize.cse_after_recomputation.cse : 0.000071s : 0.00% optimize.environ_conv : 0.000027s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000020s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000099s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000020s : 0.00% optimize.offloading_packed_experts : 0.000019s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000054s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000015s : 0.00% optimize.overlap_grad_flash_sp : 0.000078s : 0.00% 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 : 0.000266s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000047s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000058s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000222s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000063s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000073s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000897s : 0.04% validate : 0.000108s : 0.00% Time group info: ------[substitution.] 0.006702 665 1.09% : 0.000073s : 7: substitution.arithmetic_simplify 0.18% : 0.000012s : 7: substitution.depend_value_elim 0.23% : 0.000015s : 17: substitution.elim_not_effective 0.41% : 0.000027s : 20: substitution.float_tuple_getitem_switch 0.43% : 0.000029s : 13: substitution.fold_const_symbol 0.25% : 0.000017s : 19: substitution.graph_param_transform 76.58% : 0.005132s : 100: substitution.inline 0.27% : 0.000018s : 35: substitution.j_node_and_user_rematch 1.73% : 0.000116s : 7: substitution.less_batch_normalization 1.25% : 0.000084s : 3: substitution.list_to_tuple_eliminator_ 0.46% : 0.000031s : 15: substitution.minmaximum_grad 1.37% : 0.000092s : 6: substitution.opt_reshape 0.37% : 0.000025s : 35: substitution.remove_not_recompute_node 0.12% : 0.000008s : 2: substitution.replace_old_param 1.34% : 0.000090s : 29: substitution.reshape_eliminate 0.86% : 0.000058s : 21: substitution.switch_simplify 2.71% : 0.000182s : 60: substitution.tuple_list_convert_item_index_to_positive 1.32% : 0.000089s : 60: substitution.tuple_list_get_item_const_eliminator 1.99% : 0.000133s : 60: substitution.tuple_list_get_item_depend_reorder 4.50% : 0.000301s : 89: substitution.tuple_list_get_item_eliminator 2.55% : 0.000171s : 60: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.899099 2 84.77% : 1.609942s : 1: type_inference.infer 15.23% : 0.289157s : 1: type_inference.specialize ------[replace.] 0.002148 148 4.95% : 0.000106s : 7: replace.depend_value_elim 66.97% : 0.001439s : 100: replace.inline 2.94% : 0.000063s : 3: replace.list_to_tuple_eliminator_ 3.51% : 0.000075s : 3: replace.opt_reshape 14.81% : 0.000318s : 21: replace.switch_simplify 6.82% : 0.000147s : 14: replace.tuple_list_get_item_eliminator ------[match.] 0.005311 148 0.13% : 0.000007s : 7: match.depend_value_elim 95.52% : 0.005074s : 100: match.inline 1.51% : 0.000080s : 3: match.list_to_tuple_eliminator_ 1.12% : 0.000060s : 3: match.opt_reshape 0.88% : 0.000047s : 21: match.switch_simplify 0.83% : 0.000044s : 14: match.tuple_list_get_item_eliminator ------[predicate.] 0.002462 12232 0.99% : 0.000024s : 167: predicate.accumulaten_eliminater 0.25% : 0.000006s : 18: predicate.ad_related_special_op_eliminate 0.41% : 0.000010s : 66: predicate.addn_check_dump 5.29% : 0.000130s : 167: predicate.addn_zero_filter 0.98% : 0.000024s : 167: predicate.adjust_all_reduce_mul_add 2.08% : 0.000051s : 233: predicate.arithmetic_simplify 1.14% : 0.000028s : 167: predicate.cast_eliminate 0.23% : 0.000006s : 38: predicate.check_bprop_eliminate 0.38% : 0.000009s : 66: predicate.compare_switch_simplify 0.07% : 0.000002s : 19: predicate.const_output_eliminate 0.50% : 0.000012s : 70: predicate.depend_value_elim 1.07% : 0.000026s : 167: predicate.dict_get_item_const_eliminator 1.14% : 0.000028s : 167: predicate.dict_get_item_eliminator 6.34% : 0.000156s : 167: predicate.dict_set_item_eliminator 0.27% : 0.000007s : 37: predicate.dumpgradient_eliminate 0.07% : 0.000002s : 19: predicate.elim_not_effective 0.16% : 0.000004s : 19: predicate.elim_shapecalc_of_broadcastargs 1.12% : 0.000028s : 186: predicate.environ_add_const_eliminate 1.22% : 0.000030s : 186: predicate.environ_get_add_eliminate 1.10% : 0.000027s : 186: predicate.environ_get_depend_swap 1.59% : 0.000039s : 252: predicate.environ_get_eliminate 1.11% : 0.000027s : 186: predicate.environ_get_set_eliminate 1.76% : 0.000043s : 284: predicate.exchange_switch_depend_value 3.85% : 0.000095s : 284: predicate.float_depend_g_call 0.44% : 0.000011s : 66: predicate.float_environ_get_switch 0.57% : 0.000014s : 85: predicate.float_tuple_getitem_switch 0.06% : 0.000001s : 18: predicate.fold_const_symbol 0.26% : 0.000007s : 39: predicate.get_grad_eliminate 0.08% : 0.000002s : 19: predicate.graph_param_transform 0.45% : 0.000011s : 66: predicate.incorporate_call 0.36% : 0.000009s : 66: predicate.incorporate_call_switch 5.27% : 0.000130s : 594: predicate.inline 0.36% : 0.000009s : 39: predicate.inline_without_move 0.11% : 0.000003s : 39: predicate.j_node_and_user_rematch 0.35% : 0.000009s : 39: predicate.less_batch_normalization 1.40% : 0.000035s : 222: predicate.list_to_tuple_eliminator_ 2.54% : 0.000063s : 389: predicate.load_eliminater 0.41% : 0.000010s : 19: predicate.loop_unroll_after_grad 2.44% : 0.000060s : 290: predicate.loop_unroll_before_grad 1.41% : 0.000035s : 205: predicate.make_slice_get_slice_eliminator 0.44% : 0.000011s : 66: predicate.merge_addn 0.24% : 0.000006s : 38: predicate.micro_step_allgather_replace 0.25% : 0.000006s : 38: predicate.mini_step_allgather_replace 0.98% : 0.000024s : 167: predicate.minmaximum_grad 0.40% : 0.000010s : 19: predicate.mutable_eliminate 0.19% : 0.000005s : 24: predicate.opt_reshape 1.45% : 0.000036s : 19: predicate.parallel_virtual_node 3.32% : 0.000082s : 284: predicate.partial_defer_inline 1.32% : 0.000032s : 203: predicate.partial_eliminate 1.10% : 0.000027s : 167: predicate.print_const_string_wrapper 0.38% : 0.000009s : 59: predicate.reduce_all_const_elim 1.28% : 0.000032s : 167: predicate.reduce_eliminate 2.30% : 0.000057s : 389: predicate.redundant_stop_gradient_eliminater 0.13% : 0.000003s : 39: predicate.remove_not_recompute_node 0.93% : 0.000023s : 222: predicate.replace_applicator 0.14% : 0.000003s : 39: predicate.replace_old_param 0.08% : 0.000002s : 19: predicate.reset_defer_inline 1.11% : 0.000027s : 167: predicate.reshape_eliminate 0.24% : 0.000006s : 38: predicate.row_tensor_add_zeros_like 0.17% : 0.000004s : 19: predicate.row_tensor_eliminate 0.32% : 0.000008s : 38: predicate.same_eliminate 0.16% : 0.000004s : 46: predicate.set_cell_output_no_recompute 0.32% : 0.000008s : 39: predicate.shard_identity_eliminate 0.24% : 0.000006s : 37: predicate.special_op_eliminate 0.50% : 0.000012s : 66: predicate.specialize_transform 0.30% : 0.000007s : 38: predicate.split_environ_get_set_with_tuple_value 0.28% : 0.000007s : 39: predicate.stack_unstack_eliminate 0.13% : 0.000003s : 19: predicate.switch_call_monad_eliminater 2.00% : 0.000049s : 284: predicate.switch_defer_inline 2.04% : 0.000050s : 322: predicate.switch_layer_defer_inline 6.82% : 0.000168s : 701: predicate.switch_simplify 1.11% : 0.000027s : 167: predicate.tile_eliminate 0.97% : 0.000024s : 167: predicate.transpose_eliminate 1.60% : 0.000039s : 205: predicate.tuple_list_convert_item_index_to_positive 1.49% : 0.000037s : 205: predicate.tuple_list_get_item_const_eliminator 1.44% : 0.000035s : 205: predicate.tuple_list_get_item_depend_reorder 2.65% : 0.000065s : 285: predicate.tuple_list_get_item_eliminator 1.46% : 0.000036s : 205: predicate.tuple_list_get_set_item_eliminator 2.80% : 0.000069s : 271: predicate.tuple_list_set_item_eliminator 1.33% : 0.000033s : 219: predicate.tuple_to_list_eliminator_ 2.23% : 0.000055s : 389: predicate.updatestate_pure_node_eliminater 2.72% : 0.000067s : 455: predicate.updatestate_useless_node_eliminater 0.14% : 0.000003s : 19: predicate.value_based_eliminate 0.28% : 0.000007s : 39: predicate.virtual_dataset_eliminate 0.32% : 0.000008s : 39: predicate.virtual_output_eliminate 0.11% : 0.000003s : 18: predicate.virtual_view_grad_eliminate 0.15% : 0.000004s : 19: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.015743 137 46.73% : 0.007357s : 45: func_graph_cloner_run.FuncGraphClonerGraph 13.01% : 0.002049s : 17: func_graph_cloner_run.FuncGraphClonerNode 40.26% : 0.006337s : 75: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.594841 209 0.00% : 0.000004s : 1: ForceFp32Comm 6.91% : 0.248475s : 1: add_attr 6.91% : 0.248448s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.01% : 0.000271s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000890s : 1: auto_monad 0.00% : 0.000079s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.02% : 0.000762s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000105s : 1: control_data_broadcast_order 0.00% : 0.000057s : 1: convert_after_rewriter 0.00% : 0.000125s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000031s : 1: environ_conv 0.01% : 0.000277s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000110s : 1: graph_reusing 0.00% : 0.000025s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000029s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.02% : 0.000831s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.000944s : 1: mutable_eliminate 0.00% : 0.000023s : 1: offloading_packed_experts 0.00% : 0.000056s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000057s : 1: opt.transform.mutable_eliminate 6.70% : 0.240751s : 95: opt.transform.opt_a 0.00% : 0.000131s : 1: opt.transform.opt_after_cconv 0.00% : 0.000084s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000660s : 28: opt.transform.opt_b 0.01% : 0.000278s : 2: opt.transform.opt_trans_graph 0.01% : 0.000383s : 4: opt.transform.symbol_engine_opt 7.14% : 0.256597s : 1: opt_a 0.01% : 0.000356s : 1: opt_after_cconv 0.03% : 0.000912s : 1: opt_after_jit_grad 0.03% : 0.000977s : 1: opt_b 13.06% : 0.469594s : 1: optimize 0.00% : 0.000054s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000083s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000018s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000059s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000007s : 1: pipeline_split 0.01% : 0.000286s : 1: pre_auto_parallel 0.01% : 0.000343s : 1: py_interpret_to_execute 0.00% : 0.000045s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000155s : 1: remove_dup_value 0.19% : 0.006723s : 1: renormalize.infer 0.18% : 0.006646s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 5.74% : 0.206218s : 1: rewriter_after_opt_a 0.02% : 0.000868s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000023s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000727s : 1: symbol_engine_optimizer 0.01% : 0.000321s : 1: tuple_transform 52.84% : 1.899676s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[False-True-bfloat16--1-shape2] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[False-True-bfloat16--1-shape2],max_mem:120.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:39:07.853.06 [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 = 2.57127, [21] [bootstrap]: 0.00091056 [type_inference]: 2.01568 [event_method]: 0.00023449 [auto_monad]: 0.00074002 [graph_reusing]: 9.368e-05 [inline]: 3.7e-06 [add_attr]: 0.0064143, [1] [add_attr_with_inline]: 0.00639506, [1] [Cycle 1]: 0.00051058, [2] [tag_attr]: 0.00033818 [meta_addattr_fg_expand]: 8.147e-05 [parallel-infer-symbol]: 5.76e-06 [pre_auto_parallel]: 0.0003403 [insert-virtual-dataset]: 4.05e-06 [parallel-infer-symbol-second]: 1.37e-06 [dataset_repeat_opt]: 2.95998e-06 [pipeline_split]: 3.26999e-06 [optimize]: 0.545414, [53] [py_interpret_to_execute]: 0.00032919 [rewriter_before_opt_a]: 0.00097502 [opt_a]: 0.538356, [2] [Cycle 1]: 0.53588, [45] [expand_dump_flag]: 3.874e-05 [switch_simplify]: 0.196927 [loop_unroll]: 0.00030225 [a_1]: 0.145161 [with_stream_mark]: 0.0001547 [recompute_prepare]: 4.916e-05 [updatestate_depend_eliminate]: 2.87e-05 [updatestate_assign_eliminate]: 1.727e-05 [updatestate_loads_eliminate]: 1.672e-05 [parameter_eliminate]: 2.55002e-06 [a_2]: 0.00095253 [accelerated_algorithm]: 6.552e-05 [shard]: 2.81e-06 [meta_shard_fg_expand]: 3.679e-05 [shard_inline]: 2.93e-05 [merge_send_recv]: 2.316e-05 [auto_parallel]: 2.177e-05 [parallel]: 3.122e-05 [flash_sp]: 1.797e-05 [merge_comm]: 1.511e-05 [allreduce_fusion]: 1.458e-05 [matmul_add_comm_reduction]: 2.427e-05 [allreduce_slice_to_reducescatter]: 8.59989e-07 [virtual_shard_identity]: 9.01e-05 [virtual_dataset]: 2.7e-05 [get_grad_eliminate_]: 2.636e-05 [virtual_output]: 2.6e-05 [merge_forward]: 1.544e-05 [cell_reuse_recompute_pass]: 2.04999e-06 [offload_activation]: 2.874e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.42e-05 [merge_recompute_call_nodes]: 2.25002e-06 [before_grad]: 4.57e-05 [set_forward_comm_id_for_comm_node_pass]: 1.717e-05 [meta_fg_expand]: 2.59e-05 [flash_sp_send_recv_attached]: 5.05999e-06 [receive_attached]: 2.29999e-06 [after_resolve]: 3.04e-05 [a_after_grad]: 3.988e-05 [renormalize]: 0.189808 [add_forward_monad_depend]: 2.762e-05 [auto_monad_grad]: 3.03998e-06 [auto_monad_eliminator]: 0.00010082 [cse]: 0.00087917 [a_3]: 0.00019731 [Cycle 2]: 0.00245541, [45] [expand_dump_flag]: 2.88e-06 [switch_simplify]: 2.738e-05 [loop_unroll]: 2.465e-05 [a_1]: 0.00078299 [with_stream_mark]: 4.337e-05 [recompute_prepare]: 2.706e-05 [updatestate_depend_eliminate]: 1.767e-05 [updatestate_assign_eliminate]: 1.238e-05 [updatestate_loads_eliminate]: 1.204e-05 [parameter_eliminate]: 2.76e-06 [a_2]: 0.00035828 [accelerated_algorithm]: 3.59e-05 [shard]: 2.69999e-06 [meta_shard_fg_expand]: 1.438e-05 [shard_inline]: 2.44e-05 [merge_send_recv]: 2.351e-05 [auto_parallel]: 2.122e-05 [parallel]: 1.21e-05 [flash_sp]: 6.49999e-06 [merge_comm]: 1.566e-05 [allreduce_fusion]: 1.476e-05 [matmul_add_comm_reduction]: 2.591e-05 [allreduce_slice_to_reducescatter]: 1.00001e-06 [virtual_shard_identity]: 2.915e-05 [virtual_dataset]: 2.335e-05 [get_grad_eliminate_]: 2.317e-05 [virtual_output]: 2.271e-05 [merge_forward]: 1.607e-05 [cell_reuse_recompute_pass]: 3.20998e-06 [offload_activation]: 2.565e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.499e-05 [merge_recompute_call_nodes]: 1.66e-06 [before_grad]: 4.385e-05 [set_forward_comm_id_for_comm_node_pass]: 1.7e-05 [meta_fg_expand]: 1.275e-05 [flash_sp_send_recv_attached]: 1.86e-06 [receive_attached]: 2.26e-06 [after_resolve]: 2.996e-05 [a_after_grad]: 3.635e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 5.44e-06 [auto_monad_grad]: 2.83e-06 [auto_monad_eliminator]: 4.101e-05 [cse]: 0.0001057 [a_3]: 0.00015685 [py_interpret_to_execute_after_opt_a]: 4.288e-05 [slice_cell_reuse_recomputed_activation]: 1.91e-06 [rewriter_after_opt_a]: 0.00101921 [convert_after_rewriter]: 3.413e-05 [order_py_execute_after_rewriter]: 1.395e-05 [mutable_eliminate]: 0.00090396 [opt_b]: 0.00085449, [1] [Cycle 1]: 0.00084431, [7] [b_1]: 0.00059869 [b_2]: 2.668e-05 [updatestate_depend_eliminate]: 2.107e-05 [updatestate_assign_eliminate]: 1.269e-05 [updatestate_loads_eliminate]: 1.183e-05 [renormalize]: 9.89996e-07 [cse]: 0.00012744 [optimize_parallel_all_gather_comm]: 4.612e-05 [overlap_param_gather]: 1.93002e-06 [cconv]: 4.358e-05 [loop_unroll]: 0.00056595 [opt_after_cconv]: 0.00030504, [1] [Cycle 1]: 0.00029778, [7] [c_1]: 0.00012626 [parameter_eliminate]: 5.22e-06 [updatestate_depend_eliminate]: 1.879e-05 [updatestate_assign_eliminate]: 1.144e-05 [updatestate_loads_eliminate]: 1.138e-05 [cse]: 8.653e-05 [renormalize]: 5.29981e-07 [remove_dup_value]: 0.0001441 [tuple_transform]: 0.00030319, [1] [Cycle 1]: 0.00029607, [4] [d_1]: 0.00024582 [none_parameter_eliminate]: 2.61e-06 [renormalize]: 1.79978e-07 [switch_simplify]: 2.525e-05 [partial_unused_args_eliminate]: 2.20002e-06 [add_recomputation]: 0.00017939 [cse_after_recomputation]: 7.598e-05, [1] [Cycle 1]: 6.919e-05, [1] [cse]: 6.185e-05 [environ_conv]: 2.241e-05 [swap_dp_allreduce_reducescatter]: 1.951e-05 [bias_add_comm_swap]: 4.07998e-06 [label_micro_interleaved_index]: 5.61e-06 [label_fine_grained_interleaved_index]: 2.74999e-06 [merge_cast_opt]: 1.44998e-06 [slice_recompute_activation]: 2.19001e-06 [micro_interleaved_order_control]: 2.38002e-06 [assign_add_opt]: 1.14998e-06 [ForceFp32Comm]: 8.70001e-07 [remove_cast_before_assign_add]: 1.09e-06 [full_micro_interleaved_order_control]: 2.32999e-06 [reorder_send_recv_between_fp_bp]: 2.81e-06 [comm_op_add_attrs]: 9.89996e-07 [add_comm_op_reuse_tag]: 9.79984e-07 [interleave_split_concat_branches]: 1.39e-06 [interleave_parallel_branches]: 1.09e-06 [overlap_opt_shard_in_pipeline]: 1.21997e-06 [overlap_opt_shard_grad_in_pipeline]: 2.07001e-06 [control_data_broadcast_order]: 4.008e-05 [grouped_pairwise_exchange_alltoall]: 1.61998e-06 [offloading_packed_experts]: 1.209e-05 [overlap_recompute_and_grad_model_parallel]: 1.251e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.47001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.47999e-06 [overlap_recompute_comm]: 2.29999e-06 [overlap_grad_ring_attention]: 9.94001e-06 [overlap_grad_flash_sp]: 5.773e-05 [begin_end_overlap_inline]: 4.69998e-07 [split_matmul_comm_elemetwise]: 2.19999e-06 [split_layernorm_comm]: 1.70001e-06 [handle_group_info]: 1.02998e-06 [symbol_engine_optimizer]: 0.00065644, [1] [Cycle 1]: 0.00064966, [6] [build]: 0.00025642 [elim_shapecalc]: 3.707e-05 [elim_not_effective]: 5.567e-05 [opt_reshape]: 0.00018581 [fold_const_symbol]: 6.257e-05 [renormalize]: 5.50004e-07 [detach_backward]: 2.49999e-06 [pipeline_parallel_scheduler]: 1.77001e-06 [auto_monad_reorder]: 6.377e-05 [get_jit_bprop_graph]: 2.71e-06 [rewriter_after_jit_bprop_graph]: 7.83001e-06 [opt_after_jit_grad]: 0.00094831 [validate]: 0.00012757 Sums bootstrap : 0.000911s : 0.04% type_inference : 2.015677s : 78.62% event_method : 0.000234s : 0.01% auto_monad : 0.000740s : 0.03% graph_reusing : 0.000094s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000338s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000081s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000340s : 0.01% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000329s : 0.01% optimize.rewriter_before_opt_a : 0.000975s : 0.04% optimize.opt_a.expand_dump_flag : 0.000042s : 0.00% optimize.opt_a.switch_simplify : 0.196955s : 7.68% optimize.opt_a.loop_unroll : 0.000327s : 0.01% optimize.opt_a.a_1 : 0.145944s : 5.69% optimize.opt_a.with_stream_mark : 0.000198s : 0.01% optimize.opt_a.recompute_prepare : 0.000076s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000046s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000030s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000029s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.001311s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000101s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000051s : 0.00% optimize.opt_a.shard_inline : 0.000054s : 0.00% optimize.opt_a.merge_send_recv : 0.000047s : 0.00% optimize.opt_a.auto_parallel : 0.000043s : 0.00% optimize.opt_a.parallel : 0.000043s : 0.00% optimize.opt_a.flash_sp : 0.000024s : 0.00% optimize.opt_a.merge_comm : 0.000031s : 0.00% optimize.opt_a.allreduce_fusion : 0.000029s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000050s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000119s : 0.00% optimize.opt_a.virtual_dataset : 0.000050s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000050s : 0.00% optimize.opt_a.virtual_output : 0.000049s : 0.00% optimize.opt_a.merge_forward : 0.000032s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000054s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000109s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000090s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000034s : 0.00% optimize.opt_a.meta_fg_expand : 0.000039s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000060s : 0.00% optimize.opt_a.a_after_grad : 0.000076s : 0.00% optimize.opt_a.renormalize : 0.189809s : 7.40% optimize.opt_a.add_forward_monad_depend : 0.000033s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000142s : 0.01% optimize.opt_a.cse : 0.000985s : 0.04% optimize.opt_a.a_3 : 0.000354s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000043s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.001019s : 0.04% optimize.convert_after_rewriter : 0.000034s : 0.00% optimize.order_py_execute_after_rewriter : 0.000014s : 0.00% optimize.mutable_eliminate : 0.000904s : 0.04% optimize.opt_b.b_1 : 0.000599s : 0.02% optimize.opt_b.b_2 : 0.000027s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000127s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000046s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.000566s : 0.02% optimize.opt_after_cconv.c_1 : 0.000126s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.cse : 0.000087s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000144s : 0.01% optimize.tuple_transform.d_1 : 0.000246s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000179s : 0.01% optimize.cse_after_recomputation.cse : 0.000062s : 0.00% optimize.environ_conv : 0.000022s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000020s : 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 : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000040s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000012s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000013s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000058s : 0.00% optimize.begin_end_overlap_inline : 0.000000s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000256s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000037s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000056s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000186s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000063s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000064s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000948s : 0.04% validate : 0.000128s : 0.00% Time group info: ------[substitution.] 0.006386 665 1.01% : 0.000064s : 7: substitution.arithmetic_simplify 0.13% : 0.000008s : 7: substitution.depend_value_elim 0.23% : 0.000015s : 17: substitution.elim_not_effective 0.35% : 0.000022s : 20: substitution.float_tuple_getitem_switch 0.40% : 0.000025s : 13: substitution.fold_const_symbol 0.26% : 0.000017s : 19: substitution.graph_param_transform 76.47% : 0.004884s : 100: substitution.inline 0.25% : 0.000016s : 35: substitution.j_node_and_user_rematch 0.50% : 0.000032s : 7: substitution.less_batch_normalization 1.24% : 0.000079s : 3: substitution.list_to_tuple_eliminator_ 0.50% : 0.000032s : 15: substitution.minmaximum_grad 1.02% : 0.000065s : 6: substitution.opt_reshape 0.37% : 0.000024s : 35: substitution.remove_not_recompute_node 0.11% : 0.000007s : 2: substitution.replace_old_param 1.42% : 0.000091s : 29: substitution.reshape_eliminate 2.26% : 0.000144s : 21: substitution.switch_simplify 2.73% : 0.000174s : 60: substitution.tuple_list_convert_item_index_to_positive 1.42% : 0.000090s : 60: substitution.tuple_list_get_item_const_eliminator 2.20% : 0.000141s : 60: substitution.tuple_list_get_item_depend_reorder 4.65% : 0.000297s : 89: substitution.tuple_list_get_item_eliminator 2.47% : 0.000158s : 60: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.015276 2 89.60% : 1.805678s : 1: type_inference.infer 10.40% : 0.209598s : 1: type_inference.specialize ------[replace.] 0.197874 148 0.04% : 0.000071s : 7: replace.depend_value_elim 0.69% : 0.001365s : 100: replace.inline 0.03% : 0.000063s : 3: replace.list_to_tuple_eliminator_ 0.04% : 0.000070s : 3: replace.opt_reshape 99.13% : 0.196148s : 21: replace.switch_simplify 0.08% : 0.000158s : 14: replace.tuple_list_get_item_eliminator ------[match.] 0.005062 148 0.11% : 0.000005s : 7: match.depend_value_elim 93.76% : 0.004746s : 100: match.inline 1.50% : 0.000076s : 3: match.list_to_tuple_eliminator_ 1.16% : 0.000059s : 3: match.opt_reshape 2.51% : 0.000127s : 21: match.switch_simplify 0.97% : 0.000049s : 14: match.tuple_list_get_item_eliminator ------[predicate.] 0.002212 12232 1.12% : 0.000025s : 167: predicate.accumulaten_eliminater 0.32% : 0.000007s : 18: predicate.ad_related_special_op_eliminate 0.46% : 0.000010s : 66: predicate.addn_check_dump 1.09% : 0.000024s : 167: predicate.addn_zero_filter 1.12% : 0.000025s : 167: predicate.adjust_all_reduce_mul_add 2.11% : 0.000047s : 233: predicate.arithmetic_simplify 1.10% : 0.000024s : 167: predicate.cast_eliminate 0.25% : 0.000006s : 38: predicate.check_bprop_eliminate 0.47% : 0.000010s : 66: predicate.compare_switch_simplify 0.07% : 0.000002s : 19: predicate.const_output_eliminate 0.49% : 0.000011s : 70: predicate.depend_value_elim 1.21% : 0.000027s : 167: predicate.dict_get_item_const_eliminator 1.25% : 0.000028s : 167: predicate.dict_get_item_eliminator 1.13% : 0.000025s : 167: predicate.dict_set_item_eliminator 0.32% : 0.000007s : 37: predicate.dumpgradient_eliminate 0.07% : 0.000002s : 19: predicate.elim_not_effective 0.20% : 0.000004s : 19: predicate.elim_shapecalc_of_broadcastargs 1.28% : 0.000028s : 186: predicate.environ_add_const_eliminate 1.23% : 0.000027s : 186: predicate.environ_get_add_eliminate 1.19% : 0.000026s : 186: predicate.environ_get_depend_swap 1.72% : 0.000038s : 252: predicate.environ_get_eliminate 1.24% : 0.000027s : 186: predicate.environ_get_set_eliminate 1.96% : 0.000043s : 284: predicate.exchange_switch_depend_value 2.69% : 0.000060s : 284: predicate.float_depend_g_call 0.44% : 0.000010s : 66: predicate.float_environ_get_switch 0.62% : 0.000014s : 85: predicate.float_tuple_getitem_switch 0.07% : 0.000001s : 18: predicate.fold_const_symbol 0.34% : 0.000008s : 39: predicate.get_grad_eliminate 0.07% : 0.000002s : 19: predicate.graph_param_transform 0.43% : 0.000010s : 66: predicate.incorporate_call 0.42% : 0.000009s : 66: predicate.incorporate_call_switch 5.69% : 0.000126s : 594: predicate.inline 0.38% : 0.000008s : 39: predicate.inline_without_move 0.12% : 0.000003s : 39: predicate.j_node_and_user_rematch 0.39% : 0.000009s : 39: predicate.less_batch_normalization 1.71% : 0.000038s : 222: predicate.list_to_tuple_eliminator_ 2.45% : 0.000054s : 389: predicate.load_eliminater 0.32% : 0.000007s : 19: predicate.loop_unroll_after_grad 3.57% : 0.000079s : 290: predicate.loop_unroll_before_grad 1.52% : 0.000034s : 205: predicate.make_slice_get_slice_eliminator 0.43% : 0.000010s : 66: predicate.merge_addn 0.25% : 0.000006s : 38: predicate.micro_step_allgather_replace 0.26% : 0.000006s : 38: predicate.mini_step_allgather_replace 1.10% : 0.000024s : 167: predicate.minmaximum_grad 0.38% : 0.000008s : 19: predicate.mutable_eliminate 0.21% : 0.000005s : 24: predicate.opt_reshape 0.14% : 0.000003s : 19: predicate.parallel_virtual_node 3.82% : 0.000084s : 284: predicate.partial_defer_inline 1.48% : 0.000033s : 203: predicate.partial_eliminate 2.33% : 0.000051s : 167: predicate.print_const_string_wrapper 0.38% : 0.000008s : 59: predicate.reduce_all_const_elim 1.47% : 0.000033s : 167: predicate.reduce_eliminate 2.60% : 0.000057s : 389: predicate.redundant_stop_gradient_eliminater 0.14% : 0.000003s : 39: predicate.remove_not_recompute_node 1.03% : 0.000023s : 222: predicate.replace_applicator 0.16% : 0.000003s : 39: predicate.replace_old_param 0.09% : 0.000002s : 19: predicate.reset_defer_inline 1.23% : 0.000027s : 167: predicate.reshape_eliminate 0.28% : 0.000006s : 38: predicate.row_tensor_add_zeros_like 0.16% : 0.000004s : 19: predicate.row_tensor_eliminate 0.43% : 0.000010s : 38: predicate.same_eliminate 0.19% : 0.000004s : 46: predicate.set_cell_output_no_recompute 0.37% : 0.000008s : 39: predicate.shard_identity_eliminate 0.26% : 0.000006s : 37: predicate.special_op_eliminate 0.51% : 0.000011s : 66: predicate.specialize_transform 0.33% : 0.000007s : 38: predicate.split_environ_get_set_with_tuple_value 0.32% : 0.000007s : 39: predicate.stack_unstack_eliminate 0.15% : 0.000003s : 19: predicate.switch_call_monad_eliminater 2.14% : 0.000047s : 284: predicate.switch_defer_inline 2.44% : 0.000054s : 322: predicate.switch_layer_defer_inline 9.90% : 0.000219s : 701: predicate.switch_simplify 1.16% : 0.000026s : 167: predicate.tile_eliminate 1.15% : 0.000025s : 167: predicate.transpose_eliminate 1.69% : 0.000037s : 205: predicate.tuple_list_convert_item_index_to_positive 1.78% : 0.000039s : 205: predicate.tuple_list_get_item_const_eliminator 1.70% : 0.000038s : 205: predicate.tuple_list_get_item_depend_reorder 2.91% : 0.000064s : 285: predicate.tuple_list_get_item_eliminator 1.87% : 0.000041s : 205: predicate.tuple_list_get_set_item_eliminator 2.18% : 0.000048s : 271: predicate.tuple_list_set_item_eliminator 1.43% : 0.000032s : 219: predicate.tuple_to_list_eliminator_ 2.44% : 0.000054s : 389: predicate.updatestate_pure_node_eliminater 3.01% : 0.000067s : 455: predicate.updatestate_useless_node_eliminater 0.14% : 0.000003s : 19: predicate.value_based_eliminate 0.34% : 0.000008s : 39: predicate.virtual_dataset_eliminate 0.31% : 0.000007s : 39: predicate.virtual_output_eliminate 0.12% : 0.000003s : 18: predicate.virtual_view_grad_eliminate 0.16% : 0.000003s : 19: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.015220 137 50.18% : 0.007637s : 45: func_graph_cloner_run.FuncGraphClonerGraph 12.51% : 0.001905s : 17: func_graph_cloner_run.FuncGraphClonerNode 37.31% : 0.005678s : 75: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.659648 209 0.00% : 0.000003s : 1: ForceFp32Comm 0.18% : 0.006422s : 1: add_attr 0.17% : 0.006400s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.01% : 0.000187s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000760s : 1: auto_monad 0.00% : 0.000069s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.03% : 0.000958s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000044s : 1: control_data_broadcast_order 0.00% : 0.000041s : 1: convert_after_rewriter 0.00% : 0.000079s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000026s : 1: environ_conv 0.01% : 0.000245s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000008s : 1: get_jit_bprop_graph 0.00% : 0.000102s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000577s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.000919s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.00% : 0.000040s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000047s : 1: opt.transform.mutable_eliminate 9.44% : 0.345561s : 95: opt.transform.opt_a 0.00% : 0.000125s : 1: opt.transform.opt_after_cconv 0.00% : 0.000088s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000587s : 28: opt.transform.opt_b 0.01% : 0.000268s : 2: opt.transform.opt_trans_graph 0.01% : 0.000335s : 4: opt.transform.symbol_engine_opt 14.71% : 0.538363s : 1: opt_a 0.01% : 0.000309s : 1: opt_after_cconv 0.03% : 0.000965s : 1: opt_after_jit_grad 0.02% : 0.000859s : 1: opt_b 14.90% : 0.545422s : 1: optimize 0.00% : 0.000051s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000061s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000016s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000007s : 1: pipeline_split 0.01% : 0.000352s : 1: pre_auto_parallel 0.01% : 0.000342s : 1: py_interpret_to_execute 0.00% : 0.000049s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000150s : 1: remove_dup_value 0.14% : 0.005227s : 1: renormalize.infer 5.04% : 0.184556s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.001035s : 1: rewriter_after_opt_a 0.03% : 0.001005s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000023s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000660s : 1: symbol_engine_optimizer 0.01% : 0.000306s : 1: tuple_transform 55.08% : 2.015711s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[False-True-bfloat16--1-shape3] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[False-True-bfloat16--1-shape3],max_mem:116.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:39:15.982.997 [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 = 1.76437, [21] [bootstrap]: 0.00084639 [type_inference]: 1.45443 [event_method]: 0.00082583 [auto_monad]: 0.00018514 [graph_reusing]: 9.07001e-06 [inline]: 3.51999e-06 [add_attr]: 0.00503692, [1] [add_attr_with_inline]: 0.00501907, [1] [Cycle 1]: 0.00010846, [2] [tag_attr]: 5.392e-05 [meta_addattr_fg_expand]: 8.95999e-06 [parallel-infer-symbol]: 3.81999e-06 [pre_auto_parallel]: 6.228e-05 [insert-virtual-dataset]: 2.66999e-06 [parallel-infer-symbol-second]: 7.99977e-07 [dataset_repeat_opt]: 2.06998e-06 [pipeline_split]: 1.86e-06 [optimize]: 0.301814, [53] [py_interpret_to_execute]: 5.02e-05 [rewriter_before_opt_a]: 0.00016054 [opt_a]: 0.29699, [2] [Cycle 1]: 0.294617, [45] [expand_dump_flag]: 3.83001e-06 [switch_simplify]: 5.835e-05 [loop_unroll]: 4.61e-05 [a_1]: 0.00155607 [with_stream_mark]: 3.848e-05 [recompute_prepare]: 3.035e-05 [updatestate_depend_eliminate]: 1.374e-05 [updatestate_assign_eliminate]: 9.74e-06 [updatestate_loads_eliminate]: 1.106e-05 [parameter_eliminate]: 2.53e-06 [a_2]: 0.00041236 [accelerated_algorithm]: 6.23e-05 [shard]: 2.83e-06 [meta_shard_fg_expand]: 1.095e-05 [shard_inline]: 2.386e-05 [merge_send_recv]: 1.818e-05 [auto_parallel]: 4.279e-05 [parallel]: 3.248e-05 [flash_sp]: 1.518e-05 [merge_comm]: 1.458e-05 [allreduce_fusion]: 1.165e-05 [matmul_add_comm_reduction]: 2.132e-05 [allreduce_slice_to_reducescatter]: 8.30012e-07 [virtual_shard_identity]: 3.342e-05 [virtual_dataset]: 5.208e-05 [get_grad_eliminate_]: 2.939e-05 [virtual_output]: 2.955e-05 [merge_forward]: 1.368e-05 [cell_reuse_recompute_pass]: 2.02999e-06 [offload_activation]: 4.609e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.581e-05 [merge_recompute_call_nodes]: 1.47001e-06 [before_grad]: 4.041e-05 [set_forward_comm_id_for_comm_node_pass]: 1.39e-05 [meta_fg_expand]: 1.121e-05 [flash_sp_send_recv_attached]: 6.36e-06 [receive_attached]: 2.22999e-06 [after_resolve]: 2.939e-05 [a_after_grad]: 3.764e-05 [renormalize]: 0.290812 [add_forward_monad_depend]: 1.847e-05 [auto_monad_grad]: 3.63e-06 [auto_monad_eliminator]: 4.58e-05 [cse]: 0.00034921 [a_3]: 0.00017182 [Cycle 2]: 0.00235554, [45] [expand_dump_flag]: 3.26001e-06 [switch_simplify]: 2.428e-05 [loop_unroll]: 2.236e-05 [a_1]: 0.00076223 [with_stream_mark]: 3.171e-05 [recompute_prepare]: 2.285e-05 [updatestate_depend_eliminate]: 1.26e-05 [updatestate_assign_eliminate]: 1.136e-05 [updatestate_loads_eliminate]: 9.61e-06 [parameter_eliminate]: 3.27997e-06 [a_2]: 0.00031427 [accelerated_algorithm]: 3.264e-05 [shard]: 2.83e-06 [meta_shard_fg_expand]: 7.77002e-06 [shard_inline]: 2.38e-05 [merge_send_recv]: 2.099e-05 [auto_parallel]: 1.837e-05 [parallel]: 9.79e-06 [flash_sp]: 4.84e-06 [merge_comm]: 1.141e-05 [allreduce_fusion]: 1.049e-05 [matmul_add_comm_reduction]: 2.336e-05 [allreduce_slice_to_reducescatter]: 1.17e-06 [virtual_shard_identity]: 2.446e-05 [virtual_dataset]: 2.038e-05 [get_grad_eliminate_]: 1.942e-05 [virtual_output]: 2.037e-05 [merge_forward]: 1.076e-05 [cell_reuse_recompute_pass]: 3.36001e-06 [offload_activation]: 2.44e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.378e-05 [merge_recompute_call_nodes]: 1.47999e-06 [before_grad]: 3.526e-05 [set_forward_comm_id_for_comm_node_pass]: 1.353e-05 [meta_fg_expand]: 9.81e-06 [flash_sp_send_recv_attached]: 3.19001e-06 [receive_attached]: 2.21998e-06 [after_resolve]: 2.681e-05 [a_after_grad]: 3.501e-05 [renormalize]: 2.19996e-07 [add_forward_monad_depend]: 4.44002e-06 [auto_monad_grad]: 2.96999e-06 [auto_monad_eliminator]: 3.466e-05 [cse]: 9.225e-05 [a_3]: 0.00025162 [py_interpret_to_execute_after_opt_a]: 7.213e-05 [slice_cell_reuse_recomputed_activation]: 2.26998e-06 [rewriter_after_opt_a]: 0.0005307 [convert_after_rewriter]: 2.245e-05 [order_py_execute_after_rewriter]: 1.331e-05 [mutable_eliminate]: 0.00086319 [opt_b]: 0.00079041, [1] [Cycle 1]: 0.00078153, [7] [b_1]: 0.00056398 [b_2]: 2.438e-05 [updatestate_depend_eliminate]: 1.919e-05 [updatestate_assign_eliminate]: 1.047e-05 [updatestate_loads_eliminate]: 9.95002e-06 [renormalize]: 7.89994e-07 [cse]: 0.00010458 [optimize_parallel_all_gather_comm]: 4.147e-05 [overlap_param_gather]: 1.97999e-06 [cconv]: 4.143e-05 [loop_unroll]: 0.00064714 [opt_after_cconv]: 0.00027453, [1] [Cycle 1]: 0.00026456, [7] [c_1]: 0.00011131 [parameter_eliminate]: 5.47999e-06 [updatestate_depend_eliminate]: 1.715e-05 [updatestate_assign_eliminate]: 9.10999e-06 [updatestate_loads_eliminate]: 8.54e-06 [cse]: 7.337e-05 [renormalize]: 9.99979e-07 [remove_dup_value]: 0.00010669 [tuple_transform]: 0.00027165, [1] [Cycle 1]: 0.00026656, [4] [d_1]: 0.00021905 [none_parameter_eliminate]: 2.66e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 2.209e-05 [partial_unused_args_eliminate]: 2.05002e-06 [add_recomputation]: 0.00014445 [cse_after_recomputation]: 6.611e-05, [1] [Cycle 1]: 5.934e-05, [1] [cse]: 5.103e-05 [environ_conv]: 2.191e-05 [swap_dp_allreduce_reducescatter]: 1.665e-05 [bias_add_comm_swap]: 3.65003e-06 [label_micro_interleaved_index]: 5.46e-06 [label_fine_grained_interleaved_index]: 2.64999e-06 [merge_cast_opt]: 1.37e-06 [slice_recompute_activation]: 2.69999e-06 [micro_interleaved_order_control]: 2.57001e-06 [assign_add_opt]: 1.17e-06 [ForceFp32Comm]: 1.30001e-06 [remove_cast_before_assign_add]: 1.05999e-06 [full_micro_interleaved_order_control]: 2.34001e-06 [reorder_send_recv_between_fp_bp]: 2.94001e-06 [comm_op_add_attrs]: 1.23002e-06 [add_comm_op_reuse_tag]: 9.89996e-07 [interleave_split_concat_branches]: 1.18001e-06 [interleave_parallel_branches]: 1.12e-06 [overlap_opt_shard_in_pipeline]: 1.25001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.99999e-06 [control_data_broadcast_order]: 3.403e-05 [grouped_pairwise_exchange_alltoall]: 1.62001e-06 [offloading_packed_experts]: 9.57001e-06 [overlap_recompute_and_grad_model_parallel]: 1.148e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.35001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.32999e-06 [overlap_recompute_comm]: 2.39001e-06 [overlap_grad_ring_attention]: 8.40001e-06 [overlap_grad_flash_sp]: 4.856e-05 [begin_end_overlap_inline]: 5.10016e-07 [split_matmul_comm_elemetwise]: 2.29999e-06 [split_layernorm_comm]: 1.72001e-06 [handle_group_info]: 9.00007e-07 [symbol_engine_optimizer]: 0.00022966, [1] [Cycle 1]: 0.00022401, [6] [build]: 1.798e-05 [elim_shapecalc]: 3.093e-05 [elim_not_effective]: 5.384e-05 [opt_reshape]: 3.659e-05 [fold_const_symbol]: 4.785e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.56e-06 [pipeline_parallel_scheduler]: 1.96e-06 [auto_monad_reorder]: 6.091e-05 [get_jit_bprop_graph]: 2.62001e-06 [rewriter_after_jit_bprop_graph]: 7.46001e-06 [opt_after_jit_grad]: 0.00069299 [validate]: 0.0001066 Sums bootstrap : 0.000846s : 0.05% type_inference : 1.454429s : 82.73% event_method : 0.000826s : 0.05% auto_monad : 0.000185s : 0.01% graph_reusing : 0.000009s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000054s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000009s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000062s : 0.00% 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 : 0.000050s : 0.00% optimize.rewriter_before_opt_a : 0.000161s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000083s : 0.00% optimize.opt_a.loop_unroll : 0.000068s : 0.00% optimize.opt_a.a_1 : 0.002318s : 0.13% optimize.opt_a.with_stream_mark : 0.000070s : 0.00% optimize.opt_a.recompute_prepare : 0.000053s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000026s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000021s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000727s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000095s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000019s : 0.00% optimize.opt_a.shard_inline : 0.000048s : 0.00% optimize.opt_a.merge_send_recv : 0.000039s : 0.00% optimize.opt_a.auto_parallel : 0.000061s : 0.00% optimize.opt_a.parallel : 0.000042s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000026s : 0.00% optimize.opt_a.allreduce_fusion : 0.000022s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000045s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000058s : 0.00% optimize.opt_a.virtual_dataset : 0.000072s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000049s : 0.00% optimize.opt_a.virtual_output : 0.000050s : 0.00% optimize.opt_a.merge_forward : 0.000024s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000070s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000090s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000076s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000027s : 0.00% optimize.opt_a.meta_fg_expand : 0.000021s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000056s : 0.00% optimize.opt_a.a_after_grad : 0.000073s : 0.00% optimize.opt_a.renormalize : 0.290812s : 16.54% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000080s : 0.00% optimize.opt_a.cse : 0.000441s : 0.03% optimize.opt_a.a_3 : 0.000423s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000072s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000531s : 0.03% optimize.convert_after_rewriter : 0.000022s : 0.00% optimize.order_py_execute_after_rewriter : 0.000013s : 0.00% optimize.mutable_eliminate : 0.000863s : 0.05% optimize.opt_b.b_1 : 0.000564s : 0.03% optimize.opt_b.b_2 : 0.000024s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000105s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000041s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.00% optimize.loop_unroll : 0.000647s : 0.04% optimize.opt_after_cconv.c_1 : 0.000111s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.cse : 0.000073s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000107s : 0.01% optimize.tuple_transform.d_1 : 0.000219s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000022s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000144s : 0.01% optimize.cse_after_recomputation.cse : 0.000051s : 0.00% optimize.environ_conv : 0.000022s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000017s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000034s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000010s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000011s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000049s : 0.00% 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 : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000031s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000054s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000037s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000048s : 0.00% 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 : 0.000061s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000693s : 0.04% validate : 0.000107s : 0.01% Time group info: ------[substitution.] 0.000859 234 5.63% : 0.000048s : 6: substitution.arithmetic_simplify 1.22% : 0.000010s : 13: substitution.elim_not_effective 1.90% : 0.000016s : 12: substitution.float_tuple_getitem_switch 1.02% : 0.000009s : 13: substitution.fold_const_symbol 1.83% : 0.000016s : 18: substitution.graph_param_transform 42.44% : 0.000365s : 7: substitution.inline 1.73% : 0.000015s : 26: substitution.j_node_and_user_rematch 3.23% : 0.000028s : 2: substitution.less_batch_normalization 1.51% : 0.000013s : 8: substitution.minmaximum_grad 0.35% : 0.000003s : 3: substitution.opt_reshape 2.00% : 0.000017s : 26: substitution.remove_not_recompute_node 0.87% : 0.000007s : 4: substitution.replace_old_param 4.52% : 0.000039s : 8: substitution.reshape_eliminate 6.19% : 0.000053s : 16: substitution.tuple_list_convert_item_index_to_positive 2.57% : 0.000022s : 16: substitution.tuple_list_get_item_const_eliminator 3.77% : 0.000032s : 16: substitution.tuple_list_get_item_depend_reorder 11.98% : 0.000103s : 24: substitution.tuple_list_get_item_eliminator 7.26% : 0.000062s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.454282 2 99.65% : 1.449141s : 1: type_inference.infer 0.35% : 0.005141s : 1: type_inference.specialize ------[replace.] 0.000076 7 100.00% : 0.000076s : 7: replace.inline ------[match.] 0.000358 7 100.00% : 0.000358s : 7: match.inline ------[predicate.] 0.000743 4574 0.79% : 0.000006s : 44: predicate.accumulaten_eliminater 0.77% : 0.000006s : 18: predicate.ad_related_special_op_eliminate 0.67% : 0.000005s : 37: predicate.addn_check_dump 0.77% : 0.000006s : 44: predicate.addn_zero_filter 0.73% : 0.000005s : 44: predicate.adjust_all_reduce_mul_add 2.11% : 0.000016s : 81: predicate.arithmetic_simplify 0.80% : 0.000006s : 44: predicate.cast_eliminate 0.69% : 0.000005s : 36: predicate.check_bprop_eliminate 0.72% : 0.000005s : 37: predicate.compare_switch_simplify 0.19% : 0.000001s : 18: predicate.const_output_eliminate 0.66% : 0.000005s : 37: predicate.depend_value_elim 0.81% : 0.000006s : 44: predicate.dict_get_item_const_eliminator 0.97% : 0.000007s : 44: predicate.dict_get_item_eliminator 0.79% : 0.000006s : 44: predicate.dict_set_item_eliminator 0.86% : 0.000006s : 36: predicate.dumpgradient_eliminate 0.22% : 0.000002s : 18: predicate.elim_not_effective 0.47% : 0.000003s : 18: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000009s : 62: predicate.environ_add_const_eliminate 1.08% : 0.000008s : 62: predicate.environ_get_add_eliminate 1.13% : 0.000008s : 62: predicate.environ_get_depend_swap 1.84% : 0.000014s : 99: predicate.environ_get_eliminate 1.08% : 0.000008s : 62: predicate.environ_get_set_eliminate 0.88% : 0.000007s : 51: predicate.exchange_switch_depend_value 1.30% : 0.000010s : 51: predicate.float_depend_g_call 0.78% : 0.000006s : 37: predicate.float_environ_get_switch 1.13% : 0.000008s : 55: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 18: predicate.fold_const_symbol 0.83% : 0.000006s : 37: predicate.get_grad_eliminate 0.24% : 0.000002s : 18: predicate.graph_param_transform 0.70% : 0.000005s : 37: predicate.incorporate_call 0.62% : 0.000005s : 37: predicate.incorporate_call_switch 5.37% : 0.000040s : 205: predicate.inline 0.99% : 0.000007s : 37: predicate.inline_without_move 0.37% : 0.000003s : 37: predicate.j_node_and_user_rematch 1.05% : 0.000008s : 37: predicate.less_batch_normalization 1.51% : 0.000011s : 80: predicate.list_to_tuple_eliminator_ 2.15% : 0.000016s : 124: predicate.load_eliminater 0.82% : 0.000006s : 18: predicate.loop_unroll_after_grad 1.21% : 0.000009s : 66: predicate.loop_unroll_before_grad 1.65% : 0.000012s : 80: predicate.make_slice_get_slice_eliminator 0.75% : 0.000006s : 37: predicate.merge_addn 0.74% : 0.000006s : 36: predicate.micro_step_allgather_replace 0.72% : 0.000005s : 36: predicate.mini_step_allgather_replace 0.78% : 0.000006s : 44: predicate.minmaximum_grad 0.93% : 0.000007s : 18: predicate.mutable_eliminate 0.45% : 0.000003s : 18: predicate.opt_reshape 0.37% : 0.000003s : 18: predicate.parallel_virtual_node 1.38% : 0.000010s : 51: predicate.partial_defer_inline 6.13% : 0.000046s : 62: predicate.partial_eliminate 0.77% : 0.000006s : 44: predicate.print_const_string_wrapper 0.73% : 0.000005s : 37: predicate.reduce_all_const_elim 1.01% : 0.000008s : 44: predicate.reduce_eliminate 2.08% : 0.000015s : 124: predicate.redundant_stop_gradient_eliminater 0.40% : 0.000003s : 37: predicate.remove_not_recompute_node 1.20% : 0.000009s : 80: predicate.replace_applicator 0.47% : 0.000003s : 37: predicate.replace_old_param 0.25% : 0.000002s : 18: predicate.reset_defer_inline 0.96% : 0.000007s : 44: predicate.reshape_eliminate 0.79% : 0.000006s : 36: predicate.row_tensor_add_zeros_like 0.40% : 0.000003s : 18: predicate.row_tensor_eliminate 1.05% : 0.000008s : 36: predicate.same_eliminate 0.45% : 0.000003s : 37: predicate.set_cell_output_no_recompute 0.86% : 0.000006s : 37: predicate.shard_identity_eliminate 0.72% : 0.000005s : 36: predicate.special_op_eliminate 0.81% : 0.000006s : 37: predicate.specialize_transform 0.91% : 0.000007s : 36: predicate.split_environ_get_set_with_tuple_value 0.88% : 0.000007s : 37: predicate.stack_unstack_eliminate 0.38% : 0.000003s : 18: predicate.switch_call_monad_eliminater 0.98% : 0.000007s : 51: predicate.switch_defer_inline 3.95% : 0.000029s : 87: predicate.switch_layer_defer_inline 3.49% : 0.000026s : 172: predicate.switch_simplify 0.86% : 0.000006s : 44: predicate.tile_eliminate 0.75% : 0.000006s : 44: predicate.transpose_eliminate 1.67% : 0.000012s : 80: predicate.tuple_list_convert_item_index_to_positive 1.74% : 0.000013s : 80: predicate.tuple_list_get_item_const_eliminator 1.67% : 0.000012s : 80: predicate.tuple_list_get_item_depend_reorder 2.91% : 0.000022s : 117: predicate.tuple_list_get_item_eliminator 1.68% : 0.000012s : 80: predicate.tuple_list_get_set_item_eliminator 2.45% : 0.000018s : 117: predicate.tuple_list_set_item_eliminator 1.63% : 0.000012s : 80: predicate.tuple_to_list_eliminator_ 2.05% : 0.000015s : 124: predicate.updatestate_pure_node_eliminater 2.93% : 0.000022s : 161: predicate.updatestate_useless_node_eliminater 0.38% : 0.000003s : 18: predicate.value_based_eliminate 0.84% : 0.000006s : 37: predicate.virtual_dataset_eliminate 0.78% : 0.000006s : 37: predicate.virtual_output_eliminate 0.36% : 0.000003s : 18: predicate.virtual_view_grad_eliminate 0.41% : 0.000003s : 18: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.010904 54 68.68% : 0.007489s : 45: func_graph_cloner_run.FuncGraphClonerGraph 31.32% : 0.003415s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.367144 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.21% : 0.005043s : 1: add_attr 0.21% : 0.005025s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.01% : 0.000149s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000199s : 1: auto_monad 0.00% : 0.000066s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.04% : 0.000900s : 1: bootstrap 0.00% : 0.000045s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000037s : 1: control_data_broadcast_order 0.00% : 0.000028s : 1: convert_after_rewriter 0.00% : 0.000069s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000025s : 1: environ_conv 0.04% : 0.000847s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.03% : 0.000659s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.000878s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000040s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000043s : 1: opt.transform.mutable_eliminate 0.18% : 0.004169s : 78: opt.transform.opt_a 0.00% : 0.000110s : 1: opt.transform.opt_after_cconv 0.00% : 0.000079s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000547s : 28: opt.transform.opt_b 0.01% : 0.000239s : 2: opt.transform.opt_trans_graph 0.01% : 0.000163s : 4: opt.transform.symbol_engine_opt 12.55% : 0.296995s : 1: opt_a 0.01% : 0.000278s : 1: opt_after_cconv 0.03% : 0.000707s : 1: opt_after_jit_grad 0.03% : 0.000796s : 1: opt_b 12.75% : 0.301821s : 1: optimize 0.00% : 0.000045s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000017s : 1: order_py_execute_after_rewriter 0.00% : 0.000052s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 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% : 0.000015s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000067s : 1: pre_auto_parallel 0.00% : 0.000056s : 1: py_interpret_to_execute 0.00% : 0.000081s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000113s : 1: remove_dup_value 12.11% : 0.286649s : 1: renormalize.infer 0.17% : 0.004141s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000543s : 1: rewriter_after_opt_a 0.01% : 0.000165s : 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% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000020s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000233s : 1: symbol_engine_optimizer 0.01% : 0.000276s : 1: tuple_transform 61.44% : 1.454469s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[True-False-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[True-False-bfloat16--1-shape0],max_mem:116.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:39:21.864.526 [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 = 1.93262, [21] [bootstrap]: 0.00076043 [type_inference]: 1.61637 [event_method]: 0.00099025 [auto_monad]: 0.00019736 [graph_reusing]: 8.70001e-06 [inline]: 2.84001e-06 [add_attr]: 0.0848882, [1] [add_attr_with_inline]: 0.0848603, [1] [Cycle 1]: 0.0802686, [2] [tag_attr]: 0.0801421 [meta_addattr_fg_expand]: 3.265e-05 [parallel-infer-symbol]: 5.74e-06 [pre_auto_parallel]: 9.313e-05 [insert-virtual-dataset]: 2.56e-06 [parallel-infer-symbol-second]: 7.30011e-07 [dataset_repeat_opt]: 2.58e-06 [pipeline_split]: 1.60999e-06 [optimize]: 0.0195165, [53] [py_interpret_to_execute]: 6.727e-05 [rewriter_before_opt_a]: 0.00017551 [opt_a]: 0.0149588, [2] [Cycle 1]: 0.0128933, [45] [expand_dump_flag]: 5.73002e-06 [switch_simplify]: 6.269e-05 [loop_unroll]: 5.016e-05 [a_1]: 0.00156346 [with_stream_mark]: 3.676e-05 [recompute_prepare]: 3.151e-05 [updatestate_depend_eliminate]: 1.451e-05 [updatestate_assign_eliminate]: 1.006e-05 [updatestate_loads_eliminate]: 1.129e-05 [parameter_eliminate]: 3.31001e-06 [a_2]: 0.00034133 [accelerated_algorithm]: 5.11e-05 [shard]: 3.43999e-06 [meta_shard_fg_expand]: 8.50001e-06 [shard_inline]: 2.106e-05 [merge_send_recv]: 1.746e-05 [auto_parallel]: 1.712e-05 [parallel]: 2.946e-05 [flash_sp]: 1.431e-05 [merge_comm]: 1.393e-05 [allreduce_fusion]: 1.059e-05 [matmul_add_comm_reduction]: 2.117e-05 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 3.027e-05 [virtual_dataset]: 2.172e-05 [get_grad_eliminate_]: 2.071e-05 [virtual_output]: 2.234e-05 [merge_forward]: 1.115e-05 [cell_reuse_recompute_pass]: 1.52999e-06 [offload_activation]: 2.222e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.486e-05 [merge_recompute_call_nodes]: 1.45001e-06 [before_grad]: 3.933e-05 [set_forward_comm_id_for_comm_node_pass]: 1.244e-05 [meta_fg_expand]: 1.178e-05 [flash_sp_send_recv_attached]: 5.82999e-06 [receive_attached]: 2.46998e-06 [after_resolve]: 2.831e-05 [a_after_grad]: 3.737e-05 [renormalize]: 0.00928362 [add_forward_monad_depend]: 1.974e-05 [auto_monad_grad]: 3.4e-06 [auto_monad_eliminator]: 4.441e-05 [cse]: 0.00033677 [a_3]: 0.00017215 [Cycle 2]: 0.00204186, [45] [expand_dump_flag]: 2.67001e-06 [switch_simplify]: 2.398e-05 [loop_unroll]: 2.061e-05 [a_1]: 0.00067697 [with_stream_mark]: 3.1e-05 [recompute_prepare]: 2.377e-05 [updatestate_depend_eliminate]: 1.298e-05 [updatestate_assign_eliminate]: 1.141e-05 [updatestate_loads_eliminate]: 9.34e-06 [parameter_eliminate]: 2.74999e-06 [a_2]: 0.00030294 [accelerated_algorithm]: 2.608e-05 [shard]: 2.68e-06 [meta_shard_fg_expand]: 7.08998e-06 [shard_inline]: 1.922e-05 [merge_send_recv]: 1.823e-05 [auto_parallel]: 1.85e-05 [parallel]: 1.099e-05 [flash_sp]: 4.56002e-06 [merge_comm]: 1.116e-05 [allreduce_fusion]: 1.099e-05 [matmul_add_comm_reduction]: 2.334e-05 [allreduce_slice_to_reducescatter]: 8.29983e-07 [virtual_shard_identity]: 2.181e-05 [virtual_dataset]: 1.88e-05 [get_grad_eliminate_]: 1.916e-05 [virtual_output]: 1.996e-05 [merge_forward]: 1.095e-05 [cell_reuse_recompute_pass]: 3.11999e-06 [offload_activation]: 2.287e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.839e-05 [merge_recompute_call_nodes]: 1.84e-06 [before_grad]: 3.389e-05 [set_forward_comm_id_for_comm_node_pass]: 1.262e-05 [meta_fg_expand]: 9.02e-06 [flash_sp_send_recv_attached]: 1.86e-06 [receive_attached]: 2.70002e-06 [after_resolve]: 2.705e-05 [a_after_grad]: 3.276e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.74001e-06 [auto_monad_grad]: 2.16e-06 [auto_monad_eliminator]: 2.835e-05 [cse]: 8.311e-05 [a_3]: 0.00013585 [py_interpret_to_execute_after_opt_a]: 3.782e-05 [slice_cell_reuse_recomputed_activation]: 2.58003e-06 [rewriter_after_opt_a]: 0.00048543 [convert_after_rewriter]: 2.304e-05 [order_py_execute_after_rewriter]: 1.486e-05 [mutable_eliminate]: 0.00084423 [opt_b]: 0.00075356, [1] [Cycle 1]: 0.00074522, [7] [b_1]: 0.00054063 [b_2]: 2.595e-05 [updatestate_depend_eliminate]: 1.984e-05 [updatestate_assign_eliminate]: 1.004e-05 [updatestate_loads_eliminate]: 9.97001e-06 [renormalize]: 7.59988e-07 [cse]: 9.086e-05 [optimize_parallel_all_gather_comm]: 3.803e-05 [overlap_param_gather]: 1.96003e-06 [cconv]: 4.322e-05 [loop_unroll]: 0.00054768 [opt_after_cconv]: 0.00026251, [1] [Cycle 1]: 0.00025447, [7] [c_1]: 0.00010875 [parameter_eliminate]: 5.09e-06 [updatestate_depend_eliminate]: 1.639e-05 [updatestate_assign_eliminate]: 9.44e-06 [updatestate_loads_eliminate]: 8.84998e-06 [cse]: 6.843e-05 [renormalize]: 6.80011e-07 [remove_dup_value]: 0.00010514 [tuple_transform]: 0.00026441, [1] [Cycle 1]: 0.00025936, [4] [d_1]: 0.00021146 [none_parameter_eliminate]: 2.00002e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 2.241e-05 [partial_unused_args_eliminate]: 1.80001e-06 [add_recomputation]: 0.00014479 [cse_after_recomputation]: 6.379e-05, [1] [Cycle 1]: 5.721e-05, [1] [cse]: 4.976e-05 [environ_conv]: 1.971e-05 [swap_dp_allreduce_reducescatter]: 1.639e-05 [bias_add_comm_swap]: 3.05002e-06 [label_micro_interleaved_index]: 4.58999e-06 [label_fine_grained_interleaved_index]: 2.61999e-06 [merge_cast_opt]: 1.47001e-06 [slice_recompute_activation]: 2.19999e-06 [micro_interleaved_order_control]: 2.38002e-06 [assign_add_opt]: 1.19e-06 [ForceFp32Comm]: 9.00007e-07 [remove_cast_before_assign_add]: 1.05999e-06 [full_micro_interleaved_order_control]: 2.07999e-06 [reorder_send_recv_between_fp_bp]: 3.38e-06 [comm_op_add_attrs]: 1.15001e-06 [add_comm_op_reuse_tag]: 9.70002e-07 [interleave_split_concat_branches]: 1.19e-06 [interleave_parallel_branches]: 1.33002e-06 [overlap_opt_shard_in_pipeline]: 1.55001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.70001e-06 [control_data_broadcast_order]: 3.282e-05 [grouped_pairwise_exchange_alltoall]: 1.55001e-06 [offloading_packed_experts]: 1e-05 [overlap_recompute_and_grad_model_parallel]: 1.006e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.18001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.66e-06 [overlap_recompute_comm]: 2.31e-06 [overlap_grad_ring_attention]: 8.45001e-06 [overlap_grad_flash_sp]: 4.744e-05 [begin_end_overlap_inline]: 6.10016e-07 [split_matmul_comm_elemetwise]: 2.84001e-06 [split_layernorm_comm]: 1.69e-06 [handle_group_info]: 1.15001e-06 [symbol_engine_optimizer]: 0.00020006, [1] [Cycle 1]: 0.00019397, [6] [build]: 1.836e-05 [elim_shapecalc]: 2.782e-05 [elim_not_effective]: 3.74e-05 [opt_reshape]: 2.647e-05 [fold_const_symbol]: 4.742e-05 [renormalize]: 2.29978e-07 [detach_backward]: 2.56e-06 [pipeline_parallel_scheduler]: 1.59e-06 [auto_monad_reorder]: 6.098e-05 [get_jit_bprop_graph]: 1.216e-05 [rewriter_after_jit_bprop_graph]: 1.519e-05 [opt_after_jit_grad]: 0.00108584 [validate]: 0.00016492 Sums bootstrap : 0.000760s : 0.04% type_inference : 1.616371s : 94.07% event_method : 0.000990s : 0.06% auto_monad : 0.000197s : 0.01% graph_reusing : 0.000009s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.080142s : 4.66% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000033s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000093s : 0.01% 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 : 0.000067s : 0.00% optimize.rewriter_before_opt_a : 0.000176s : 0.01% optimize.opt_a.expand_dump_flag : 0.000008s : 0.00% optimize.opt_a.switch_simplify : 0.000087s : 0.01% optimize.opt_a.loop_unroll : 0.000071s : 0.00% optimize.opt_a.a_1 : 0.002240s : 0.13% optimize.opt_a.with_stream_mark : 0.000068s : 0.00% optimize.opt_a.recompute_prepare : 0.000055s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000027s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000021s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000644s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000077s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000016s : 0.00% optimize.opt_a.shard_inline : 0.000040s : 0.00% optimize.opt_a.merge_send_recv : 0.000036s : 0.00% optimize.opt_a.auto_parallel : 0.000036s : 0.00% optimize.opt_a.parallel : 0.000040s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000025s : 0.00% optimize.opt_a.allreduce_fusion : 0.000022s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000045s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000052s : 0.00% optimize.opt_a.virtual_dataset : 0.000041s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000040s : 0.00% optimize.opt_a.virtual_output : 0.000042s : 0.00% optimize.opt_a.merge_forward : 0.000022s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000045s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000083s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000073s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000025s : 0.00% optimize.opt_a.meta_fg_expand : 0.000021s : 0.00% 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 : 0.000055s : 0.00% optimize.opt_a.a_after_grad : 0.000070s : 0.00% optimize.opt_a.renormalize : 0.009284s : 0.54% optimize.opt_a.add_forward_monad_depend : 0.000022s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000073s : 0.00% optimize.opt_a.cse : 0.000420s : 0.02% optimize.opt_a.a_3 : 0.000308s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000038s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000485s : 0.03% optimize.convert_after_rewriter : 0.000023s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000844s : 0.05% optimize.opt_b.b_1 : 0.000541s : 0.03% optimize.opt_b.b_2 : 0.000026s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000091s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000038s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000043s : 0.00% optimize.loop_unroll : 0.000548s : 0.03% optimize.opt_after_cconv.c_1 : 0.000109s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000016s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.cse : 0.000068s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000105s : 0.01% optimize.tuple_transform.d_1 : 0.000211s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000022s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000145s : 0.01% optimize.cse_after_recomputation.cse : 0.000050s : 0.00% optimize.environ_conv : 0.000020s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000016s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000033s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000010s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 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 : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000047s : 0.00% 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 : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000028s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000037s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000026s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000047s : 0.00% 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 : 0.000061s : 0.00% get_jit_bprop_graph : 0.000012s : 0.00% rewriter_after_jit_bprop_graph : 0.000015s : 0.00% opt_after_jit_grad : 0.001086s : 0.06% validate : 0.000165s : 0.01% Time group info: ------[substitution.] 0.000793 234 6.13% : 0.000049s : 6: substitution.arithmetic_simplify 0.70% : 0.000006s : 13: substitution.elim_not_effective 2.05% : 0.000016s : 12: substitution.float_tuple_getitem_switch 1.08% : 0.000009s : 13: substitution.fold_const_symbol 1.94% : 0.000015s : 18: substitution.graph_param_transform 47.05% : 0.000373s : 7: substitution.inline 1.89% : 0.000015s : 26: substitution.j_node_and_user_rematch 3.03% : 0.000024s : 2: substitution.less_batch_normalization 1.73% : 0.000014s : 8: substitution.minmaximum_grad 0.25% : 0.000002s : 3: substitution.opt_reshape 2.10% : 0.000017s : 26: substitution.remove_not_recompute_node 0.83% : 0.000007s : 4: substitution.replace_old_param 5.03% : 0.000040s : 8: substitution.reshape_eliminate 6.47% : 0.000051s : 16: substitution.tuple_list_convert_item_index_to_positive 2.90% : 0.000023s : 16: substitution.tuple_list_get_item_const_eliminator 3.94% : 0.000031s : 16: substitution.tuple_list_get_item_depend_reorder 9.05% : 0.000072s : 24: substitution.tuple_list_get_item_eliminator 3.83% : 0.000030s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.616217 2 99.67% : 1.610946s : 1: type_inference.infer 0.33% : 0.005271s : 1: type_inference.specialize ------[replace.] 0.000069 7 100.00% : 0.000069s : 7: replace.inline ------[match.] 0.000366 7 100.00% : 0.000366s : 7: match.inline ------[predicate.] 0.000705 4574 0.89% : 0.000006s : 44: predicate.accumulaten_eliminater 1.95% : 0.000014s : 18: predicate.ad_related_special_op_eliminate 0.74% : 0.000005s : 37: predicate.addn_check_dump 0.94% : 0.000007s : 44: predicate.addn_zero_filter 0.86% : 0.000006s : 44: predicate.adjust_all_reduce_mul_add 2.13% : 0.000015s : 81: predicate.arithmetic_simplify 0.89% : 0.000006s : 44: predicate.cast_eliminate 0.78% : 0.000005s : 36: predicate.check_bprop_eliminate 0.71% : 0.000005s : 37: predicate.compare_switch_simplify 0.22% : 0.000002s : 18: predicate.const_output_eliminate 0.80% : 0.000006s : 37: predicate.depend_value_elim 0.93% : 0.000007s : 44: predicate.dict_get_item_const_eliminator 0.97% : 0.000007s : 44: predicate.dict_get_item_eliminator 0.86% : 0.000006s : 44: predicate.dict_set_item_eliminator 1.22% : 0.000009s : 36: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 18: predicate.elim_not_effective 0.39% : 0.000003s : 18: predicate.elim_shapecalc_of_broadcastargs 1.28% : 0.000009s : 62: predicate.environ_add_const_eliminate 1.22% : 0.000009s : 62: predicate.environ_get_add_eliminate 1.22% : 0.000009s : 62: predicate.environ_get_depend_swap 1.95% : 0.000014s : 99: predicate.environ_get_eliminate 1.23% : 0.000009s : 62: predicate.environ_get_set_eliminate 1.00% : 0.000007s : 51: predicate.exchange_switch_depend_value 1.47% : 0.000010s : 51: predicate.float_depend_g_call 0.72% : 0.000005s : 37: predicate.float_environ_get_switch 1.25% : 0.000009s : 55: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 18: predicate.fold_const_symbol 0.83% : 0.000006s : 37: predicate.get_grad_eliminate 0.26% : 0.000002s : 18: predicate.graph_param_transform 0.73% : 0.000005s : 37: predicate.incorporate_call 0.69% : 0.000005s : 37: predicate.incorporate_call_switch 5.40% : 0.000038s : 205: predicate.inline 0.94% : 0.000007s : 37: predicate.inline_without_move 0.40% : 0.000003s : 37: predicate.j_node_and_user_rematch 0.97% : 0.000007s : 37: predicate.less_batch_normalization 1.69% : 0.000012s : 80: predicate.list_to_tuple_eliminator_ 2.36% : 0.000017s : 124: predicate.load_eliminater 0.80% : 0.000006s : 18: predicate.loop_unroll_after_grad 1.36% : 0.000010s : 66: predicate.loop_unroll_before_grad 1.74% : 0.000012s : 80: predicate.make_slice_get_slice_eliminator 0.82% : 0.000006s : 37: predicate.merge_addn 0.74% : 0.000005s : 36: predicate.micro_step_allgather_replace 0.69% : 0.000005s : 36: predicate.mini_step_allgather_replace 0.84% : 0.000006s : 44: predicate.minmaximum_grad 1.05% : 0.000007s : 18: predicate.mutable_eliminate 0.44% : 0.000003s : 18: predicate.opt_reshape 0.47% : 0.000003s : 18: predicate.parallel_virtual_node 1.52% : 0.000011s : 51: predicate.partial_defer_inline 1.26% : 0.000009s : 62: predicate.partial_eliminate 0.85% : 0.000006s : 44: predicate.print_const_string_wrapper 0.75% : 0.000005s : 37: predicate.reduce_all_const_elim 1.12% : 0.000008s : 44: predicate.reduce_eliminate 2.35% : 0.000017s : 124: predicate.redundant_stop_gradient_eliminater 0.40% : 0.000003s : 37: predicate.remove_not_recompute_node 1.22% : 0.000009s : 80: predicate.replace_applicator 0.47% : 0.000003s : 37: predicate.replace_old_param 0.27% : 0.000002s : 18: predicate.reset_defer_inline 1.04% : 0.000007s : 44: predicate.reshape_eliminate 0.74% : 0.000005s : 36: predicate.row_tensor_add_zeros_like 0.45% : 0.000003s : 18: predicate.row_tensor_eliminate 1.10% : 0.000008s : 36: predicate.same_eliminate 0.47% : 0.000003s : 37: predicate.set_cell_output_no_recompute 0.92% : 0.000006s : 37: predicate.shard_identity_eliminate 0.80% : 0.000006s : 36: predicate.special_op_eliminate 0.86% : 0.000006s : 37: predicate.specialize_transform 0.86% : 0.000006s : 36: predicate.split_environ_get_set_with_tuple_value 0.93% : 0.000007s : 37: predicate.stack_unstack_eliminate 0.37% : 0.000003s : 18: predicate.switch_call_monad_eliminater 1.13% : 0.000008s : 51: predicate.switch_defer_inline 1.76% : 0.000012s : 87: predicate.switch_layer_defer_inline 3.84% : 0.000027s : 172: predicate.switch_simplify 0.87% : 0.000006s : 44: predicate.tile_eliminate 0.92% : 0.000007s : 44: predicate.transpose_eliminate 1.80% : 0.000013s : 80: predicate.tuple_list_convert_item_index_to_positive 1.98% : 0.000014s : 80: predicate.tuple_list_get_item_const_eliminator 1.71% : 0.000012s : 80: predicate.tuple_list_get_item_depend_reorder 2.94% : 0.000021s : 117: predicate.tuple_list_get_item_eliminator 1.71% : 0.000012s : 80: predicate.tuple_list_get_set_item_eliminator 2.59% : 0.000018s : 117: predicate.tuple_list_set_item_eliminator 1.55% : 0.000011s : 80: predicate.tuple_to_list_eliminator_ 2.26% : 0.000016s : 124: predicate.updatestate_pure_node_eliminater 3.14% : 0.000022s : 161: predicate.updatestate_useless_node_eliminater 0.43% : 0.000003s : 18: predicate.value_based_eliminate 0.80% : 0.000006s : 37: predicate.virtual_dataset_eliminate 0.79% : 0.000006s : 37: predicate.virtual_output_eliminate 0.36% : 0.000003s : 18: predicate.virtual_view_grad_eliminate 0.43% : 0.000003s : 18: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.009905 54 75.58% : 0.007486s : 45: func_graph_cloner_run.FuncGraphClonerGraph 24.42% : 0.002419s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.051004 192 0.00% : 0.000003s : 1: ForceFp32Comm 4.14% : 0.084897s : 1: add_attr 4.14% : 0.084869s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000150s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000212s : 1: auto_monad 10.15% : 0.208169s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.04% : 0.000838s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000036s : 1: control_data_broadcast_order 0.00% : 0.000029s : 1: convert_after_rewriter 0.00% : 0.000067s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000023s : 1: environ_conv 0.05% : 0.001014s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000023s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000007s : 1: label_micro_interleaved_index 0.03% : 0.000560s : 1: loop_unroll 0.00% : 0.000007s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.000857s : 1: mutable_eliminate 0.00% : 0.000013s : 1: offloading_packed_experts 0.00% : 0.000033s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000043s : 1: opt.transform.mutable_eliminate 0.19% : 0.003845s : 78: opt.transform.opt_a 0.01% : 0.000107s : 1: opt.transform.opt_after_cconv 0.01% : 0.000121s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000528s : 28: opt.transform.opt_b 0.01% : 0.000231s : 2: opt.transform.opt_trans_graph 0.01% : 0.000134s : 4: opt.transform.symbol_engine_opt 0.73% : 0.014963s : 1: opt_a 0.01% : 0.000266s : 1: opt_after_cconv 0.05% : 0.001112s : 1: opt_after_jit_grad 0.04% : 0.000757s : 1: opt_b 0.95% : 0.019524s : 1: optimize 0.00% : 0.000042s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000052s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 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% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.00% : 0.000101s : 1: pre_auto_parallel 0.00% : 0.000076s : 1: py_interpret_to_execute 0.00% : 0.000042s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000111s : 1: remove_dup_value 0.30% : 0.006248s : 1: renormalize.infer 0.15% : 0.003015s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000020s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000498s : 1: rewriter_after_opt_a 0.01% : 0.000183s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000019s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000203s : 1: symbol_engine_optimizer 0.01% : 0.000269s : 1: tuple_transform 78.81% : 1.616410s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[True-False-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[True-False-bfloat16--1-shape1],max_mem:120.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:39:31.228.828 [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 = 1.90176, [21] [bootstrap]: 0.00075567 [type_inference]: 1.67745 [event_method]: 0.0027115 [auto_monad]: 0.00019879 [graph_reusing]: 8.91002e-06 [inline]: 3.58e-06 [add_attr]: 0.00589524, [1] [add_attr_with_inline]: 0.00587657, [1] [Cycle 1]: 9.69e-05, [2] [tag_attr]: 4.729e-05 [meta_addattr_fg_expand]: 8.38999e-06 [parallel-infer-symbol]: 3.24001e-06 [pre_auto_parallel]: 5.736e-05 [insert-virtual-dataset]: 2.87002e-06 [parallel-infer-symbol-second]: 8.89995e-07 [dataset_repeat_opt]: 2.06998e-06 [pipeline_split]: 1.69998e-06 [optimize]: 0.213284, [53] [py_interpret_to_execute]: 4.915e-05 [rewriter_before_opt_a]: 0.00015969 [opt_a]: 0.207967, [2] [Cycle 1]: 0.205497, [45] [expand_dump_flag]: 4.28999e-06 [switch_simplify]: 5.978e-05 [loop_unroll]: 4.587e-05 [a_1]: 0.00148526 [with_stream_mark]: 3.548e-05 [recompute_prepare]: 3.003e-05 [updatestate_depend_eliminate]: 1.425e-05 [updatestate_assign_eliminate]: 9.65002e-06 [updatestate_loads_eliminate]: 1.225e-05 [parameter_eliminate]: 2.74999e-06 [a_2]: 0.00038421 [accelerated_algorithm]: 5.453e-05 [shard]: 2.37999e-06 [meta_shard_fg_expand]: 9.46e-06 [shard_inline]: 2.321e-05 [merge_send_recv]: 1.852e-05 [auto_parallel]: 1.719e-05 [parallel]: 3.078e-05 [flash_sp]: 1.548e-05 [merge_comm]: 1.417e-05 [allreduce_fusion]: 1.213e-05 [matmul_add_comm_reduction]: 2.15e-05 [allreduce_slice_to_reducescatter]: 8.59989e-07 [virtual_shard_identity]: 3.235e-05 [virtual_dataset]: 2.802e-05 [get_grad_eliminate_]: 2.706e-05 [virtual_output]: 2.899e-05 [merge_forward]: 1.327e-05 [cell_reuse_recompute_pass]: 1.78002e-06 [offload_activation]: 2.373e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.317e-05 [merge_recompute_call_nodes]: 1.57001e-06 [before_grad]: 4.706e-05 [set_forward_comm_id_for_comm_node_pass]: 1.582e-05 [meta_fg_expand]: 1.016e-05 [flash_sp_send_recv_attached]: 6.01e-06 [receive_attached]: 2.58e-06 [after_resolve]: 3.461e-05 [a_after_grad]: 4.941e-05 [renormalize]: 0.201843 [add_forward_monad_depend]: 2.144e-05 [auto_monad_grad]: 3.78001e-06 [auto_monad_eliminator]: 4.806e-05 [cse]: 0.00036097 [a_3]: 0.00016982 [Cycle 2]: 0.00245337, [45] [expand_dump_flag]: 2.70997e-06 [switch_simplify]: 2.5e-05 [loop_unroll]: 2.146e-05 [a_1]: 0.00091014 [with_stream_mark]: 3.78e-05 [recompute_prepare]: 2.667e-05 [updatestate_depend_eliminate]: 1.46e-05 [updatestate_assign_eliminate]: 1.125e-05 [updatestate_loads_eliminate]: 9.94001e-06 [parameter_eliminate]: 3.21001e-06 [a_2]: 0.00031136 [accelerated_algorithm]: 3.036e-05 [shard]: 2.74001e-06 [meta_shard_fg_expand]: 8.85001e-06 [shard_inline]: 2.048e-05 [merge_send_recv]: 1.948e-05 [auto_parallel]: 1.807e-05 [parallel]: 1.122e-05 [flash_sp]: 4.71002e-06 [merge_comm]: 1.14e-05 [allreduce_fusion]: 1.113e-05 [matmul_add_comm_reduction]: 2.354e-05 [allreduce_slice_to_reducescatter]: 1.16002e-06 [virtual_shard_identity]: 2.393e-05 [virtual_dataset]: 1.924e-05 [get_grad_eliminate_]: 1.951e-05 [virtual_output]: 1.964e-05 [merge_forward]: 1.087e-05 [cell_reuse_recompute_pass]: 3.55998e-06 [offload_activation]: 2.556e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.289e-05 [merge_recompute_call_nodes]: 1.52001e-06 [before_grad]: 3.581e-05 [set_forward_comm_id_for_comm_node_pass]: 1.293e-05 [meta_fg_expand]: 9.97001e-06 [flash_sp_send_recv_attached]: 2.46e-06 [receive_attached]: 2.58e-06 [after_resolve]: 2.818e-05 [a_after_grad]: 3.413e-05 [renormalize]: 9.00181e-08 [add_forward_monad_depend]: 3.56001e-06 [auto_monad_grad]: 3.28998e-06 [auto_monad_eliminator]: 8.798e-05 [cse]: 0.00010197 [a_3]: 0.00014635 [py_interpret_to_execute_after_opt_a]: 3.8e-05 [slice_cell_reuse_recomputed_activation]: 2.71999e-06 [rewriter_after_opt_a]: 0.0004948 [convert_after_rewriter]: 2.463e-05 [order_py_execute_after_rewriter]: 1.435e-05 [mutable_eliminate]: 0.00088685 [opt_b]: 0.00093212, [1] [Cycle 1]: 0.00091142, [7] [b_1]: 0.00054071 [b_2]: 9.748e-05 [updatestate_depend_eliminate]: 2.162e-05 [updatestate_assign_eliminate]: 1.07e-05 [updatestate_loads_eliminate]: 9.91998e-06 [renormalize]: 9.99979e-07 [cse]: 0.00017454 [optimize_parallel_all_gather_comm]: 4.708e-05 [overlap_param_gather]: 2.30002e-06 [cconv]: 6.849e-05 [loop_unroll]: 0.00095653 [opt_after_cconv]: 0.00029174, [1] [Cycle 1]: 0.0002825, [7] [c_1]: 0.00011303 [parameter_eliminate]: 7.41999e-06 [updatestate_depend_eliminate]: 1.992e-05 [updatestate_assign_eliminate]: 8.64e-06 [updatestate_loads_eliminate]: 8.50001e-06 [cse]: 8.501e-05 [renormalize]: 1.14998e-06 [remove_dup_value]: 0.00010967 [tuple_transform]: 0.00028714, [1] [Cycle 1]: 0.00028127, [4] [d_1]: 0.00022992 [none_parameter_eliminate]: 3.28e-06 [renormalize]: 3.19997e-07 [switch_simplify]: 2.325e-05 [partial_unused_args_eliminate]: 2.54999e-06 [add_recomputation]: 0.000157 [cse_after_recomputation]: 6.898e-05, [1] [Cycle 1]: 6.182e-05, [1] [cse]: 5.427e-05 [environ_conv]: 2.41e-05 [swap_dp_allreduce_reducescatter]: 1.698e-05 [bias_add_comm_swap]: 3.43999e-06 [label_micro_interleaved_index]: 7.17002e-06 [label_fine_grained_interleaved_index]: 3.00002e-06 [merge_cast_opt]: 1.59998e-06 [slice_recompute_activation]: 2.48e-06 [micro_interleaved_order_control]: 2.68998e-06 [assign_add_opt]: 1.52001e-06 [ForceFp32Comm]: 1.02e-06 [remove_cast_before_assign_add]: 1.39e-06 [full_micro_interleaved_order_control]: 2.19001e-06 [reorder_send_recv_between_fp_bp]: 3.41001e-06 [comm_op_add_attrs]: 1.06997e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.24e-06 [interleave_parallel_branches]: 1.08001e-06 [overlap_opt_shard_in_pipeline]: 1.21002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.77999e-06 [control_data_broadcast_order]: 3.638e-05 [grouped_pairwise_exchange_alltoall]: 1.80001e-06 [offloading_packed_experts]: 1.085e-05 [overlap_recompute_and_grad_model_parallel]: 1.181e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.15001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.41002e-06 [overlap_recompute_comm]: 2.48002e-06 [overlap_grad_ring_attention]: 8.35999e-06 [overlap_grad_flash_sp]: 5.009e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.51e-06 [split_layernorm_comm]: 2.12001e-06 [handle_group_info]: 1.06002e-06 [symbol_engine_optimizer]: 0.00020082, [1] [Cycle 1]: 0.00019507, [6] [build]: 1.999e-05 [elim_shapecalc]: 3.201e-05 [elim_not_effective]: 3.941e-05 [opt_reshape]: 2.889e-05 [fold_const_symbol]: 3.823e-05 [renormalize]: 2.30008e-07 [detach_backward]: 2.49001e-06 [pipeline_parallel_scheduler]: 1.60001e-06 [auto_monad_reorder]: 4.655e-05 [get_jit_bprop_graph]: 2.26e-06 [rewriter_after_jit_bprop_graph]: 7.85998e-06 [opt_after_jit_grad]: 0.00082915 [validate]: 0.00018265 Sums bootstrap : 0.000756s : 0.04% type_inference : 1.677449s : 88.55% event_method : 0.002711s : 0.14% auto_monad : 0.000199s : 0.01% graph_reusing : 0.000009s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000047s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000003s : 0.00% pre_auto_parallel : 0.000057s : 0.00% 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 : 0.000049s : 0.00% optimize.rewriter_before_opt_a : 0.000160s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000085s : 0.00% optimize.opt_a.loop_unroll : 0.000067s : 0.00% optimize.opt_a.a_1 : 0.002395s : 0.13% optimize.opt_a.with_stream_mark : 0.000073s : 0.00% optimize.opt_a.recompute_prepare : 0.000057s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000029s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000696s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000085s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000018s : 0.00% optimize.opt_a.shard_inline : 0.000044s : 0.00% optimize.opt_a.merge_send_recv : 0.000038s : 0.00% optimize.opt_a.auto_parallel : 0.000035s : 0.00% optimize.opt_a.parallel : 0.000042s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000026s : 0.00% optimize.opt_a.allreduce_fusion : 0.000023s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000045s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000056s : 0.00% optimize.opt_a.virtual_dataset : 0.000047s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000047s : 0.00% optimize.opt_a.virtual_output : 0.000049s : 0.00% optimize.opt_a.merge_forward : 0.000024s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000049s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000096s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000083s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000029s : 0.00% optimize.opt_a.meta_fg_expand : 0.000020s : 0.00% 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 : 0.000063s : 0.00% optimize.opt_a.a_after_grad : 0.000084s : 0.00% optimize.opt_a.renormalize : 0.201843s : 10.65% optimize.opt_a.add_forward_monad_depend : 0.000025s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000136s : 0.01% optimize.opt_a.cse : 0.000463s : 0.02% optimize.opt_a.a_3 : 0.000316s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000038s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000495s : 0.03% optimize.convert_after_rewriter : 0.000025s : 0.00% optimize.order_py_execute_after_rewriter : 0.000014s : 0.00% optimize.mutable_eliminate : 0.000887s : 0.05% optimize.opt_b.b_1 : 0.000541s : 0.03% optimize.opt_b.b_2 : 0.000097s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000175s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000047s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000068s : 0.00% optimize.loop_unroll : 0.000957s : 0.05% optimize.opt_after_cconv.c_1 : 0.000113s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.cse : 0.000085s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000110s : 0.01% optimize.tuple_transform.d_1 : 0.000230s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000023s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000157s : 0.01% optimize.cse_after_recomputation.cse : 0.000054s : 0.00% optimize.environ_conv : 0.000024s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000017s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000036s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000050s : 0.00% 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 : 0.000020s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000032s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000039s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000029s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000038s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000047s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000829s : 0.04% validate : 0.000183s : 0.01% Time group info: ------[substitution.] 0.000811 234 5.89% : 0.000048s : 6: substitution.arithmetic_simplify 0.86% : 0.000007s : 13: substitution.elim_not_effective 2.07% : 0.000017s : 12: substitution.float_tuple_getitem_switch 0.58% : 0.000005s : 13: substitution.fold_const_symbol 1.93% : 0.000016s : 18: substitution.graph_param_transform 44.23% : 0.000359s : 7: substitution.inline 1.68% : 0.000014s : 26: substitution.j_node_and_user_rematch 3.23% : 0.000026s : 2: substitution.less_batch_normalization 1.73% : 0.000014s : 8: substitution.minmaximum_grad 0.26% : 0.000002s : 3: substitution.opt_reshape 2.29% : 0.000019s : 26: substitution.remove_not_recompute_node 0.94% : 0.000008s : 4: substitution.replace_old_param 4.96% : 0.000040s : 8: substitution.reshape_eliminate 7.04% : 0.000057s : 16: substitution.tuple_list_convert_item_index_to_positive 2.82% : 0.000023s : 16: substitution.tuple_list_get_item_const_eliminator 4.16% : 0.000034s : 16: substitution.tuple_list_get_item_depend_reorder 11.12% : 0.000090s : 24: substitution.tuple_list_get_item_eliminator 4.19% : 0.000034s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.677251 2 99.71% : 1.672311s : 1: type_inference.infer 0.29% : 0.004940s : 1: type_inference.specialize ------[replace.] 0.000072 7 100.00% : 0.000072s : 7: replace.inline ------[match.] 0.000354 7 100.00% : 0.000354s : 7: match.inline ------[predicate.] 0.000807 4574 0.80% : 0.000006s : 44: predicate.accumulaten_eliminater 0.83% : 0.000007s : 18: predicate.ad_related_special_op_eliminate 0.63% : 0.000005s : 37: predicate.addn_check_dump 0.70% : 0.000006s : 44: predicate.addn_zero_filter 14.60% : 0.000118s : 44: predicate.adjust_all_reduce_mul_add 1.91% : 0.000015s : 81: predicate.arithmetic_simplify 0.77% : 0.000006s : 44: predicate.cast_eliminate 0.72% : 0.000006s : 36: predicate.check_bprop_eliminate 0.63% : 0.000005s : 37: predicate.compare_switch_simplify 0.18% : 0.000001s : 18: predicate.const_output_eliminate 0.70% : 0.000006s : 37: predicate.depend_value_elim 0.77% : 0.000006s : 44: predicate.dict_get_item_const_eliminator 0.81% : 0.000007s : 44: predicate.dict_get_item_eliminator 0.74% : 0.000006s : 44: predicate.dict_set_item_eliminator 0.76% : 0.000006s : 36: predicate.dumpgradient_eliminate 0.18% : 0.000001s : 18: predicate.elim_not_effective 0.46% : 0.000004s : 18: predicate.elim_shapecalc_of_broadcastargs 1.01% : 0.000008s : 62: predicate.environ_add_const_eliminate 0.99% : 0.000008s : 62: predicate.environ_get_add_eliminate 0.97% : 0.000008s : 62: predicate.environ_get_depend_swap 1.74% : 0.000014s : 99: predicate.environ_get_eliminate 0.99% : 0.000008s : 62: predicate.environ_get_set_eliminate 0.83% : 0.000007s : 51: predicate.exchange_switch_depend_value 1.29% : 0.000010s : 51: predicate.float_depend_g_call 0.67% : 0.000005s : 37: predicate.float_environ_get_switch 1.11% : 0.000009s : 55: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 18: predicate.fold_const_symbol 0.69% : 0.000006s : 37: predicate.get_grad_eliminate 0.19% : 0.000002s : 18: predicate.graph_param_transform 0.65% : 0.000005s : 37: predicate.incorporate_call 0.68% : 0.000005s : 37: predicate.incorporate_call_switch 4.66% : 0.000038s : 205: predicate.inline 0.85% : 0.000007s : 37: predicate.inline_without_move 0.33% : 0.000003s : 37: predicate.j_node_and_user_rematch 0.95% : 0.000008s : 37: predicate.less_batch_normalization 1.43% : 0.000012s : 80: predicate.list_to_tuple_eliminator_ 2.00% : 0.000016s : 124: predicate.load_eliminater 0.90% : 0.000007s : 18: predicate.loop_unroll_after_grad 1.14% : 0.000009s : 66: predicate.loop_unroll_before_grad 1.47% : 0.000012s : 80: predicate.make_slice_get_slice_eliminator 0.67% : 0.000005s : 37: predicate.merge_addn 0.65% : 0.000005s : 36: predicate.micro_step_allgather_replace 0.62% : 0.000005s : 36: predicate.mini_step_allgather_replace 0.72% : 0.000006s : 44: predicate.minmaximum_grad 0.96% : 0.000008s : 18: predicate.mutable_eliminate 0.48% : 0.000004s : 18: predicate.opt_reshape 0.35% : 0.000003s : 18: predicate.parallel_virtual_node 1.38% : 0.000011s : 51: predicate.partial_defer_inline 1.12% : 0.000009s : 62: predicate.partial_eliminate 0.67% : 0.000005s : 44: predicate.print_const_string_wrapper 0.61% : 0.000005s : 37: predicate.reduce_all_const_elim 0.95% : 0.000008s : 44: predicate.reduce_eliminate 1.99% : 0.000016s : 124: predicate.redundant_stop_gradient_eliminater 0.36% : 0.000003s : 37: predicate.remove_not_recompute_node 1.12% : 0.000009s : 80: predicate.replace_applicator 0.40% : 0.000003s : 37: predicate.replace_old_param 0.25% : 0.000002s : 18: predicate.reset_defer_inline 0.95% : 0.000008s : 44: predicate.reshape_eliminate 0.68% : 0.000005s : 36: predicate.row_tensor_add_zeros_like 0.40% : 0.000003s : 18: predicate.row_tensor_eliminate 0.84% : 0.000007s : 36: predicate.same_eliminate 0.40% : 0.000003s : 37: predicate.set_cell_output_no_recompute 0.82% : 0.000007s : 37: predicate.shard_identity_eliminate 0.73% : 0.000006s : 36: predicate.special_op_eliminate 0.75% : 0.000006s : 37: predicate.specialize_transform 0.89% : 0.000007s : 36: predicate.split_environ_get_set_with_tuple_value 0.81% : 0.000007s : 37: predicate.stack_unstack_eliminate 0.35% : 0.000003s : 18: predicate.switch_call_monad_eliminater 0.96% : 0.000008s : 51: predicate.switch_defer_inline 1.51% : 0.000012s : 87: predicate.switch_layer_defer_inline 3.32% : 0.000027s : 172: predicate.switch_simplify 0.76% : 0.000006s : 44: predicate.tile_eliminate 0.83% : 0.000007s : 44: predicate.transpose_eliminate 1.61% : 0.000013s : 80: predicate.tuple_list_convert_item_index_to_positive 1.56% : 0.000013s : 80: predicate.tuple_list_get_item_const_eliminator 1.52% : 0.000012s : 80: predicate.tuple_list_get_item_depend_reorder 2.71% : 0.000022s : 117: predicate.tuple_list_get_item_eliminator 1.63% : 0.000013s : 80: predicate.tuple_list_get_set_item_eliminator 2.28% : 0.000018s : 117: predicate.tuple_list_set_item_eliminator 1.44% : 0.000012s : 80: predicate.tuple_to_list_eliminator_ 1.96% : 0.000016s : 124: predicate.updatestate_pure_node_eliminater 2.69% : 0.000022s : 161: predicate.updatestate_useless_node_eliminater 0.32% : 0.000003s : 18: predicate.value_based_eliminate 0.66% : 0.000005s : 37: predicate.virtual_dataset_eliminate 0.68% : 0.000006s : 37: predicate.virtual_output_eliminate 0.33% : 0.000003s : 18: predicate.virtual_view_grad_eliminate 0.42% : 0.000003s : 18: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.010241 54 73.91% : 0.007569s : 45: func_graph_cloner_run.FuncGraphClonerGraph 26.09% : 0.002672s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.327842 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.25% : 0.005903s : 1: add_attr 0.25% : 0.005881s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000164s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.01% : 0.000211s : 1: auto_monad 0.00% : 0.000052s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.04% : 0.000855s : 1: bootstrap 0.00% : 0.000074s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000041s : 1: control_data_broadcast_order 0.00% : 0.000031s : 1: convert_after_rewriter 0.00% : 0.000072s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000028s : 1: environ_conv 0.12% : 0.002749s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.04% : 0.000974s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.04% : 0.000902s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.00% : 0.000047s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000053s : 1: opt.transform.mutable_eliminate 0.18% : 0.004130s : 78: opt.transform.opt_a 0.00% : 0.000111s : 1: opt.transform.opt_after_cconv 0.00% : 0.000085s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000598s : 28: opt.transform.opt_b 0.01% : 0.000250s : 2: opt.transform.opt_trans_graph 0.01% : 0.000134s : 4: opt.transform.symbol_engine_opt 8.93% : 0.207972s : 1: opt_a 0.01% : 0.000296s : 1: opt_after_cconv 0.04% : 0.000844s : 1: opt_after_jit_grad 0.04% : 0.000937s : 1: opt_b 9.16% : 0.213292s : 1: optimize 0.00% : 0.000051s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000054s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.00% : 0.000063s : 1: pre_auto_parallel 0.00% : 0.000054s : 1: py_interpret_to_execute 0.00% : 0.000042s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000115s : 1: remove_dup_value 8.53% : 0.198500s : 1: renormalize.infer 0.14% : 0.003320s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000508s : 1: rewriter_after_opt_a 0.01% : 0.000165s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000021s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000204s : 1: symbol_engine_optimizer 0.01% : 0.000292s : 1: tuple_transform 72.06% : 1.677479s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[True-False-bfloat16--1-shape2] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[True-False-bfloat16--1-shape2],max_mem:120.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:39:37.358.751 [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 = 2.14802, [21] [bootstrap]: 0.00079774 [type_inference]: 1.71002 [event_method]: 0.00124004 [auto_monad]: 0.0002141 [graph_reusing]: 9.04e-06 [inline]: 2.82002e-06 [add_attr]: 0.224556, [1] [add_attr_with_inline]: 0.224535, [1] [Cycle 1]: 0.0001056, [2] [tag_attr]: 4.603e-05 [meta_addattr_fg_expand]: 8.84e-06 [parallel-infer-symbol]: 4.47998e-06 [pre_auto_parallel]: 6.435e-05 [insert-virtual-dataset]: 2.84999e-06 [parallel-infer-symbol-second]: 6.60017e-07 [dataset_repeat_opt]: 2.14999e-06 [pipeline_split]: 1.67001e-06 [optimize]: 0.209712, [53] [py_interpret_to_execute]: 5.868e-05 [rewriter_before_opt_a]: 0.00016925 [opt_a]: 0.204473, [2] [Cycle 1]: 0.0139868, [45] [expand_dump_flag]: 3.58999e-06 [switch_simplify]: 5.941e-05 [loop_unroll]: 4.54e-05 [a_1]: 0.00155545 [with_stream_mark]: 4.198e-05 [recompute_prepare]: 3.209e-05 [updatestate_depend_eliminate]: 1.416e-05 [updatestate_assign_eliminate]: 9.98002e-06 [updatestate_loads_eliminate]: 1.29e-05 [parameter_eliminate]: 2.91e-06 [a_2]: 0.00041051 [accelerated_algorithm]: 0.00012439 [shard]: 3.71001e-06 [meta_shard_fg_expand]: 1.048e-05 [shard_inline]: 2.515e-05 [merge_send_recv]: 2.003e-05 [auto_parallel]: 2.091e-05 [parallel]: 3.537e-05 [flash_sp]: 1.919e-05 [merge_comm]: 1.717e-05 [allreduce_fusion]: 1.2e-05 [matmul_add_comm_reduction]: 2.316e-05 [allreduce_slice_to_reducescatter]: 8.39995e-07 [virtual_shard_identity]: 3.576e-05 [virtual_dataset]: 2.909e-05 [get_grad_eliminate_]: 3.175e-05 [virtual_output]: 3.267e-05 [merge_forward]: 1.628e-05 [cell_reuse_recompute_pass]: 2.58e-06 [offload_activation]: 2.52e-05 [cell_reuse_handle_not_recompute_node_pass]: 6.124e-05 [merge_recompute_call_nodes]: 1.91e-06 [before_grad]: 4.602e-05 [set_forward_comm_id_for_comm_node_pass]: 1.639e-05 [meta_fg_expand]: 1.199e-05 [flash_sp_send_recv_attached]: 7.77002e-06 [receive_attached]: 2.39999e-06 [after_resolve]: 3.526e-05 [a_after_grad]: 3.989e-05 [renormalize]: 0.0101098 [add_forward_monad_depend]: 1.775e-05 [auto_monad_grad]: 2.97002e-06 [auto_monad_eliminator]: 4.535e-05 [cse]: 0.00032959 [a_3]: 0.00016911 [Cycle 2]: 0.190469, [45] [expand_dump_flag]: 2.44999e-06 [switch_simplify]: 2.507e-05 [loop_unroll]: 2.159e-05 [a_1]: 0.188747 [with_stream_mark]: 5.48e-05 [recompute_prepare]: 3.427e-05 [updatestate_depend_eliminate]: 1.387e-05 [updatestate_assign_eliminate]: 1.252e-05 [updatestate_loads_eliminate]: 9.42999e-06 [parameter_eliminate]: 3.06999e-06 [a_2]: 0.0003418 [accelerated_algorithm]: 3.159e-05 [shard]: 3.48e-06 [meta_shard_fg_expand]: 1.306e-05 [shard_inline]: 2.259e-05 [merge_send_recv]: 2.127e-05 [auto_parallel]: 1.959e-05 [parallel]: 1.098e-05 [flash_sp]: 4.77e-06 [merge_comm]: 1.238e-05 [allreduce_fusion]: 1.192e-05 [matmul_add_comm_reduction]: 2.489e-05 [allreduce_slice_to_reducescatter]: 1.32e-06 [virtual_shard_identity]: 2.737e-05 [virtual_dataset]: 2.315e-05 [get_grad_eliminate_]: 2.183e-05 [virtual_output]: 2.146e-05 [merge_forward]: 1.554e-05 [cell_reuse_recompute_pass]: 3.88001e-06 [offload_activation]: 2.719e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.916e-05 [merge_recompute_call_nodes]: 1.39998e-06 [before_grad]: 3.808e-05 [set_forward_comm_id_for_comm_node_pass]: 1.76e-05 [meta_fg_expand]: 1.183e-05 [flash_sp_send_recv_attached]: 1.69e-06 [receive_attached]: 2.32999e-06 [after_resolve]: 3.365e-05 [a_after_grad]: 3.705e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 5.63002e-06 [auto_monad_grad]: 3.34001e-06 [auto_monad_eliminator]: 4.57e-05 [cse]: 0.00011466 [a_3]: 0.00015284 [py_interpret_to_execute_after_opt_a]: 4.205e-05 [slice_cell_reuse_recomputed_activation]: 2.88998e-06 [rewriter_after_opt_a]: 0.00053477 [convert_after_rewriter]: 2.828e-05 [order_py_execute_after_rewriter]: 1.425e-05 [mutable_eliminate]: 0.00089248 [opt_b]: 0.00081873, [1] [Cycle 1]: 0.00080818, [7] [b_1]: 0.00057016 [b_2]: 2.484e-05 [updatestate_depend_eliminate]: 2.379e-05 [updatestate_assign_eliminate]: 1.035e-05 [updatestate_loads_eliminate]: 1.065e-05 [renormalize]: 1.12e-06 [cse]: 0.0001115 [optimize_parallel_all_gather_comm]: 4.163e-05 [overlap_param_gather]: 2.29999e-06 [cconv]: 4.758e-05 [loop_unroll]: 0.00069905 [opt_after_cconv]: 0.00034911, [1] [Cycle 1]: 0.00033775, [7] [c_1]: 0.00015883 [parameter_eliminate]: 7.00998e-06 [updatestate_depend_eliminate]: 2.129e-05 [updatestate_assign_eliminate]: 9.47001e-06 [updatestate_loads_eliminate]: 8.69e-06 [cse]: 8.723e-05 [renormalize]: 3.29979e-07 [remove_dup_value]: 0.00011365 [tuple_transform]: 0.00044974, [1] [Cycle 1]: 0.00044309, [4] [d_1]: 0.00038305 [none_parameter_eliminate]: 3.22002e-06 [renormalize]: 4.69998e-07 [switch_simplify]: 2.449e-05 [partial_unused_args_eliminate]: 2.26e-06 [add_recomputation]: 0.00015389 [cse_after_recomputation]: 9.688e-05, [1] [Cycle 1]: 8.923e-05, [1] [cse]: 7.932e-05 [environ_conv]: 2.39e-05 [swap_dp_allreduce_reducescatter]: 1.872e-05 [bias_add_comm_swap]: 4.26001e-06 [label_micro_interleaved_index]: 5.64e-06 [label_fine_grained_interleaved_index]: 2.86999e-06 [merge_cast_opt]: 1.62999e-06 [slice_recompute_activation]: 2.06e-06 [micro_interleaved_order_control]: 2.84999e-06 [assign_add_opt]: 1.25999e-06 [ForceFp32Comm]: 8.80013e-07 [remove_cast_before_assign_add]: 1.09003e-06 [full_micro_interleaved_order_control]: 2.53e-06 [reorder_send_recv_between_fp_bp]: 2.85998e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 1.01002e-06 [interleave_split_concat_branches]: 1.23002e-06 [interleave_parallel_branches]: 1.06002e-06 [overlap_opt_shard_in_pipeline]: 1.19e-06 [overlap_opt_shard_grad_in_pipeline]: 1.79998e-06 [control_data_broadcast_order]: 3.511e-05 [grouped_pairwise_exchange_alltoall]: 1.67001e-06 [offloading_packed_experts]: 1.103e-05 [overlap_recompute_and_grad_model_parallel]: 1.116e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.20001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.34e-06 [overlap_recompute_comm]: 2.04999e-06 [overlap_grad_ring_attention]: 8.94998e-06 [overlap_grad_flash_sp]: 4.878e-05 [begin_end_overlap_inline]: 8.2e-07 [split_matmul_comm_elemetwise]: 2.51e-06 [split_layernorm_comm]: 2.26998e-06 [handle_group_info]: 1.07998e-06 [symbol_engine_optimizer]: 0.00020351, [1] [Cycle 1]: 0.00019762, [6] [build]: 2.096e-05 [elim_shapecalc]: 3.478e-05 [elim_not_effective]: 4.036e-05 [opt_reshape]: 2.742e-05 [fold_const_symbol]: 3.395e-05 [renormalize]: 4.50003e-07 [detach_backward]: 2.32001e-06 [pipeline_parallel_scheduler]: 1.52999e-06 [auto_monad_reorder]: 4.723e-05 [get_jit_bprop_graph]: 2.31e-06 [rewriter_after_jit_bprop_graph]: 6.95998e-06 [opt_after_jit_grad]: 0.0009271 [validate]: 0.00011545 Sums bootstrap : 0.000798s : 0.04% type_inference : 1.710023s : 88.98% event_method : 0.001240s : 0.06% auto_monad : 0.000214s : 0.01% graph_reusing : 0.000009s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000046s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000009s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000064s : 0.00% 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 : 0.000059s : 0.00% optimize.rewriter_before_opt_a : 0.000169s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000084s : 0.00% optimize.opt_a.loop_unroll : 0.000067s : 0.00% optimize.opt_a.a_1 : 0.190303s : 9.90% optimize.opt_a.with_stream_mark : 0.000097s : 0.01% optimize.opt_a.recompute_prepare : 0.000066s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000028s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000023s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000752s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000156s : 0.01% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000024s : 0.00% optimize.opt_a.shard_inline : 0.000048s : 0.00% optimize.opt_a.merge_send_recv : 0.000041s : 0.00% optimize.opt_a.auto_parallel : 0.000040s : 0.00% optimize.opt_a.parallel : 0.000046s : 0.00% optimize.opt_a.flash_sp : 0.000024s : 0.00% optimize.opt_a.merge_comm : 0.000030s : 0.00% optimize.opt_a.allreduce_fusion : 0.000024s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000048s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000063s : 0.00% optimize.opt_a.virtual_dataset : 0.000052s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000054s : 0.00% optimize.opt_a.virtual_output : 0.000054s : 0.00% optimize.opt_a.merge_forward : 0.000032s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000052s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000110s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000084s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000034s : 0.00% optimize.opt_a.meta_fg_expand : 0.000024s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000069s : 0.00% optimize.opt_a.a_after_grad : 0.000077s : 0.00% optimize.opt_a.renormalize : 0.010110s : 0.53% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000091s : 0.00% optimize.opt_a.cse : 0.000444s : 0.02% optimize.opt_a.a_3 : 0.000322s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000042s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000535s : 0.03% optimize.convert_after_rewriter : 0.000028s : 0.00% optimize.order_py_execute_after_rewriter : 0.000014s : 0.00% optimize.mutable_eliminate : 0.000892s : 0.05% optimize.opt_b.b_1 : 0.000570s : 0.03% optimize.opt_b.b_2 : 0.000025s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000112s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000042s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000048s : 0.00% optimize.loop_unroll : 0.000699s : 0.04% optimize.opt_after_cconv.c_1 : 0.000159s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.cse : 0.000087s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000114s : 0.01% optimize.tuple_transform.d_1 : 0.000383s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000024s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000154s : 0.01% optimize.cse_after_recomputation.cse : 0.000079s : 0.00% optimize.environ_conv : 0.000024s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000019s : 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 : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000035s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000011s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000009s : 0.00% optimize.overlap_grad_flash_sp : 0.000049s : 0.00% 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 : 0.000021s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000035s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000040s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000027s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000034s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000047s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000927s : 0.05% validate : 0.000115s : 0.01% Time group info: ------[substitution.] 0.000943 234 6.18% : 0.000058s : 6: substitution.arithmetic_simplify 0.73% : 0.000007s : 13: substitution.elim_not_effective 1.96% : 0.000019s : 12: substitution.float_tuple_getitem_switch 0.47% : 0.000004s : 13: substitution.fold_const_symbol 1.88% : 0.000018s : 18: substitution.graph_param_transform 39.66% : 0.000374s : 7: substitution.inline 1.61% : 0.000015s : 26: substitution.j_node_and_user_rematch 9.09% : 0.000086s : 2: substitution.less_batch_normalization 1.67% : 0.000016s : 8: substitution.minmaximum_grad 0.23% : 0.000002s : 3: substitution.opt_reshape 1.90% : 0.000018s : 26: substitution.remove_not_recompute_node 1.01% : 0.000010s : 4: substitution.replace_old_param 5.78% : 0.000054s : 8: substitution.reshape_eliminate 6.55% : 0.000062s : 16: substitution.tuple_list_convert_item_index_to_positive 2.63% : 0.000025s : 16: substitution.tuple_list_get_item_const_eliminator 3.94% : 0.000037s : 16: substitution.tuple_list_get_item_depend_reorder 10.67% : 0.000101s : 24: substitution.tuple_list_get_item_eliminator 4.04% : 0.000038s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.709864 2 99.67% : 1.704181s : 1: type_inference.infer 0.33% : 0.005683s : 1: type_inference.specialize ------[replace.] 0.000081 7 100.00% : 0.000081s : 7: replace.inline ------[match.] 0.000369 7 100.00% : 0.000369s : 7: match.inline ------[predicate.] 0.000836 4574 0.76% : 0.000006s : 44: predicate.accumulaten_eliminater 0.83% : 0.000007s : 18: predicate.ad_related_special_op_eliminate 0.60% : 0.000005s : 37: predicate.addn_check_dump 0.76% : 0.000006s : 44: predicate.addn_zero_filter 0.74% : 0.000006s : 44: predicate.adjust_all_reduce_mul_add 2.05% : 0.000017s : 81: predicate.arithmetic_simplify 0.88% : 0.000007s : 44: predicate.cast_eliminate 0.61% : 0.000005s : 36: predicate.check_bprop_eliminate 0.60% : 0.000005s : 37: predicate.compare_switch_simplify 0.18% : 0.000001s : 18: predicate.const_output_eliminate 0.68% : 0.000006s : 37: predicate.depend_value_elim 0.76% : 0.000006s : 44: predicate.dict_get_item_const_eliminator 0.79% : 0.000007s : 44: predicate.dict_get_item_eliminator 0.76% : 0.000006s : 44: predicate.dict_set_item_eliminator 0.89% : 0.000007s : 36: predicate.dumpgradient_eliminate 0.18% : 0.000002s : 18: predicate.elim_not_effective 0.46% : 0.000004s : 18: predicate.elim_shapecalc_of_broadcastargs 1.02% : 0.000009s : 62: predicate.environ_add_const_eliminate 0.99% : 0.000008s : 62: predicate.environ_get_add_eliminate 1.04% : 0.000009s : 62: predicate.environ_get_depend_swap 1.90% : 0.000016s : 99: predicate.environ_get_eliminate 1.02% : 0.000009s : 62: predicate.environ_get_set_eliminate 0.83% : 0.000007s : 51: predicate.exchange_switch_depend_value 1.21% : 0.000010s : 51: predicate.float_depend_g_call 0.70% : 0.000006s : 37: predicate.float_environ_get_switch 1.04% : 0.000009s : 55: predicate.float_tuple_getitem_switch 0.16% : 0.000001s : 18: predicate.fold_const_symbol 0.86% : 0.000007s : 37: predicate.get_grad_eliminate 0.20% : 0.000002s : 18: predicate.graph_param_transform 0.67% : 0.000006s : 37: predicate.incorporate_call 0.63% : 0.000005s : 37: predicate.incorporate_call_switch 4.72% : 0.000039s : 205: predicate.inline 1.10% : 0.000009s : 37: predicate.inline_without_move 0.36% : 0.000003s : 37: predicate.j_node_and_user_rematch 1.03% : 0.000009s : 37: predicate.less_batch_normalization 1.48% : 0.000012s : 80: predicate.list_to_tuple_eliminator_ 1.92% : 0.000016s : 124: predicate.load_eliminater 0.98% : 0.000008s : 18: predicate.loop_unroll_after_grad 1.08% : 0.000009s : 66: predicate.loop_unroll_before_grad 1.46% : 0.000012s : 80: predicate.make_slice_get_slice_eliminator 0.63% : 0.000005s : 37: predicate.merge_addn 0.61% : 0.000005s : 36: predicate.micro_step_allgather_replace 0.59% : 0.000005s : 36: predicate.mini_step_allgather_replace 0.74% : 0.000006s : 44: predicate.minmaximum_grad 1.11% : 0.000009s : 18: predicate.mutable_eliminate 0.39% : 0.000003s : 18: predicate.opt_reshape 0.40% : 0.000003s : 18: predicate.parallel_virtual_node 1.71% : 0.000014s : 51: predicate.partial_defer_inline 1.30% : 0.000011s : 62: predicate.partial_eliminate 0.75% : 0.000006s : 44: predicate.print_const_string_wrapper 0.75% : 0.000006s : 37: predicate.reduce_all_const_elim 1.04% : 0.000009s : 44: predicate.reduce_eliminate 2.04% : 0.000017s : 124: predicate.redundant_stop_gradient_eliminater 0.37% : 0.000003s : 37: predicate.remove_not_recompute_node 1.14% : 0.000010s : 80: predicate.replace_applicator 0.41% : 0.000003s : 37: predicate.replace_old_param 0.22% : 0.000002s : 18: predicate.reset_defer_inline 0.91% : 0.000008s : 44: predicate.reshape_eliminate 0.72% : 0.000006s : 36: predicate.row_tensor_add_zeros_like 0.43% : 0.000004s : 18: predicate.row_tensor_eliminate 0.83% : 0.000007s : 36: predicate.same_eliminate 0.45% : 0.000004s : 37: predicate.set_cell_output_no_recompute 0.86% : 0.000007s : 37: predicate.shard_identity_eliminate 0.69% : 0.000006s : 36: predicate.special_op_eliminate 0.76% : 0.000006s : 37: predicate.specialize_transform 0.83% : 0.000007s : 36: predicate.split_environ_get_set_with_tuple_value 0.85% : 0.000007s : 37: predicate.stack_unstack_eliminate 0.33% : 0.000003s : 18: predicate.switch_call_monad_eliminater 0.88% : 0.000007s : 51: predicate.switch_defer_inline 1.54% : 0.000013s : 87: predicate.switch_layer_defer_inline 3.16% : 0.000026s : 172: predicate.switch_simplify 0.83% : 0.000007s : 44: predicate.tile_eliminate 0.69% : 0.000006s : 44: predicate.transpose_eliminate 11.86% : 0.000099s : 80: predicate.tuple_list_convert_item_index_to_positive 1.71% : 0.000014s : 80: predicate.tuple_list_get_item_const_eliminator 1.46% : 0.000012s : 80: predicate.tuple_list_get_item_depend_reorder 2.97% : 0.000025s : 117: predicate.tuple_list_get_item_eliminator 1.56% : 0.000013s : 80: predicate.tuple_list_get_set_item_eliminator 2.25% : 0.000019s : 117: predicate.tuple_list_set_item_eliminator 1.62% : 0.000014s : 80: predicate.tuple_to_list_eliminator_ 1.94% : 0.000016s : 124: predicate.updatestate_pure_node_eliminater 4.18% : 0.000035s : 161: predicate.updatestate_useless_node_eliminater 0.34% : 0.000003s : 18: predicate.value_based_eliminate 0.74% : 0.000006s : 37: predicate.virtual_dataset_eliminate 0.78% : 0.000006s : 37: predicate.virtual_output_eliminate 0.32% : 0.000003s : 18: predicate.virtual_view_grad_eliminate 0.36% : 0.000003s : 18: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.186103 54 98.53% : 0.183358s : 45: func_graph_cloner_run.FuncGraphClonerGraph 1.47% : 0.002745s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.785800 192 0.00% : 0.000003s : 1: ForceFp32Comm 8.06% : 0.224563s : 1: add_attr 8.06% : 0.224542s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000160s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000227s : 1: auto_monad 0.00% : 0.000052s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.03% : 0.000864s : 1: bootstrap 0.00% : 0.000052s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000039s : 1: control_data_broadcast_order 0.00% : 0.000034s : 1: convert_after_rewriter 0.00% : 0.000101s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000028s : 1: environ_conv 0.05% : 0.001276s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000006s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.03% : 0.000714s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.000907s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.00% : 0.000047s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000054s : 1: opt.transform.mutable_eliminate 6.90% : 0.192203s : 78: opt.transform.opt_a 0.01% : 0.000157s : 1: opt.transform.opt_after_cconv 0.01% : 0.000140s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000551s : 28: opt.transform.opt_b 0.01% : 0.000404s : 2: opt.transform.opt_trans_graph 0.00% : 0.000132s : 4: opt.transform.symbol_engine_opt 7.34% : 0.204478s : 1: opt_a 0.01% : 0.000353s : 1: opt_after_cconv 0.03% : 0.000944s : 1: opt_after_jit_grad 0.03% : 0.000824s : 1: opt_b 7.53% : 0.209720s : 1: optimize 0.00% : 0.000047s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000053s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 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% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000071s : 1: pre_auto_parallel 0.00% : 0.000065s : 1: py_interpret_to_execute 0.00% : 0.000048s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000119s : 1: remove_dup_value 0.24% : 0.006678s : 1: renormalize.infer 0.12% : 0.003407s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000550s : 1: rewriter_after_opt_a 0.01% : 0.000175s : 1: rewriter_before_opt_a 0.00% : 0.000008s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000022s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000207s : 1: symbol_engine_optimizer 0.02% : 0.000455s : 1: tuple_transform 61.38% : 1.710062s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[True-False-bfloat16--1-shape3] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[True-False-bfloat16--1-shape3],max_mem:116.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:39:43.415.807 [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 = 2.57659, [21] [bootstrap]: 0.160377 [type_inference]: 1.72415 [event_method]: 0.00147768 [auto_monad]: 0.0121587 [graph_reusing]: 0.00011684 [inline]: 3.40003e-06 [add_attr]: 0.174408, [1] [add_attr_with_inline]: 0.174384, [1] [Cycle 1]: 0.00041742, [2] [tag_attr]: 0.00023358 [meta_addattr_fg_expand]: 5.778e-05 [parallel-infer-symbol]: 5.87999e-06 [pre_auto_parallel]: 0.00029271 [insert-virtual-dataset]: 4.79e-06 [parallel-infer-symbol-second]: 1.72999e-06 [dataset_repeat_opt]: 2.80997e-06 [pipeline_split]: 3.35e-06 [optimize]: 0.502209, [53] [py_interpret_to_execute]: 0.00023751 [rewriter_before_opt_a]: 0.00084705 [opt_a]: 0.494304, [2] [Cycle 1]: 0.491842, [45] [expand_dump_flag]: 3.182e-05 [switch_simplify]: 0.00082196 [loop_unroll]: 0.00026456 [a_1]: 0.137302 [with_stream_mark]: 0.00016637 [recompute_prepare]: 5.422e-05 [updatestate_depend_eliminate]: 2.981e-05 [updatestate_assign_eliminate]: 1.817e-05 [updatestate_loads_eliminate]: 1.867e-05 [parameter_eliminate]: 4.21001e-06 [a_2]: 0.00122492 [accelerated_algorithm]: 7.118e-05 [shard]: 3.48999e-06 [meta_shard_fg_expand]: 3.915e-05 [shard_inline]: 2.928e-05 [merge_send_recv]: 2.33e-05 [auto_parallel]: 2.186e-05 [parallel]: 3.065e-05 [flash_sp]: 1.534e-05 [merge_comm]: 1.574e-05 [allreduce_fusion]: 1.487e-05 [matmul_add_comm_reduction]: 2.43e-05 [allreduce_slice_to_reducescatter]: 1.07e-06 [virtual_shard_identity]: 3.377e-05 [virtual_dataset]: 4.609e-05 [get_grad_eliminate_]: 2.92e-05 [virtual_output]: 2.632e-05 [merge_forward]: 1.746e-05 [cell_reuse_recompute_pass]: 2.22001e-06 [offload_activation]: 2.797e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.754e-05 [merge_recompute_call_nodes]: 2.31998e-06 [before_grad]: 5.145e-05 [set_forward_comm_id_for_comm_node_pass]: 6.872e-05 [meta_fg_expand]: 3.117e-05 [flash_sp_send_recv_attached]: 7.55e-06 [receive_attached]: 2.31998e-06 [after_resolve]: 4.179e-05 [a_after_grad]: 4.163e-05 [renormalize]: 0.349968 [add_forward_monad_depend]: 2.372e-05 [auto_monad_grad]: 3.09001e-06 [auto_monad_eliminator]: 6.879e-05 [cse]: 0.00040028 [a_3]: 0.00019209 [Cycle 2]: 0.0024417, [45] [expand_dump_flag]: 3.71001e-06 [switch_simplify]: 2.825e-05 [loop_unroll]: 2.537e-05 [a_1]: 0.00078587 [with_stream_mark]: 4.094e-05 [recompute_prepare]: 2.796e-05 [updatestate_depend_eliminate]: 1.638e-05 [updatestate_assign_eliminate]: 1.272e-05 [updatestate_loads_eliminate]: 1.266e-05 [parameter_eliminate]: 2.44999e-06 [a_2]: 0.00036353 [accelerated_algorithm]: 3.833e-05 [shard]: 3.04999e-06 [meta_shard_fg_expand]: 9.51e-06 [shard_inline]: 2.525e-05 [merge_send_recv]: 2.395e-05 [auto_parallel]: 2.077e-05 [parallel]: 1.104e-05 [flash_sp]: 7.15e-06 [merge_comm]: 1.436e-05 [allreduce_fusion]: 1.379e-05 [matmul_add_comm_reduction]: 2.76e-05 [allreduce_slice_to_reducescatter]: 8.40024e-07 [virtual_shard_identity]: 2.77e-05 [virtual_dataset]: 2.537e-05 [get_grad_eliminate_]: 2.315e-05 [virtual_output]: 2.458e-05 [merge_forward]: 1.503e-05 [cell_reuse_recompute_pass]: 3.65998e-06 [offload_activation]: 2.649e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.399e-05 [merge_recompute_call_nodes]: 1.55999e-06 [before_grad]: 4.217e-05 [set_forward_comm_id_for_comm_node_pass]: 1.551e-05 [meta_fg_expand]: 1.171e-05 [flash_sp_send_recv_attached]: 2.76e-06 [receive_attached]: 2.72001e-06 [after_resolve]: 3.101e-05 [a_after_grad]: 3.826e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 4.52e-06 [auto_monad_grad]: 2.82002e-06 [auto_monad_eliminator]: 3.968e-05 [cse]: 9.876e-05 [a_3]: 0.0001589 [py_interpret_to_execute_after_opt_a]: 8.355e-05 [slice_cell_reuse_recomputed_activation]: 2.24999e-06 [rewriter_after_opt_a]: 0.00106275 [convert_after_rewriter]: 3.696e-05 [order_py_execute_after_rewriter]: 1.432e-05 [mutable_eliminate]: 0.00093417 [opt_b]: 0.00090052, [1] [Cycle 1]: 0.00088975, [7] [b_1]: 0.00061826 [b_2]: 2.965e-05 [updatestate_depend_eliminate]: 2.484e-05 [updatestate_assign_eliminate]: 1.232e-05 [updatestate_loads_eliminate]: 1.145e-05 [renormalize]: 1.19e-06 [cse]: 0.00013837 [optimize_parallel_all_gather_comm]: 5.153e-05 [overlap_param_gather]: 2.40002e-06 [cconv]: 4.953e-05 [loop_unroll]: 0.00068546 [opt_after_cconv]: 0.00036186, [1] [Cycle 1]: 0.0003522, [7] [c_1]: 0.00015031 [parameter_eliminate]: 5.84999e-06 [updatestate_depend_eliminate]: 2.335e-05 [updatestate_assign_eliminate]: 1.235e-05 [updatestate_loads_eliminate]: 1.176e-05 [cse]: 0.00010529 [renormalize]: 8.50006e-07 [remove_dup_value]: 0.00014813 [tuple_transform]: 0.00085713, [1] [Cycle 1]: 0.00084901, [4] [d_1]: 0.00076842 [none_parameter_eliminate]: 4.67e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 3.09e-05 [partial_unused_args_eliminate]: 2.56998e-06 [add_recomputation]: 0.00019493 [cse_after_recomputation]: 0.00012952, [1] [Cycle 1]: 0.00011943, [1] [cse]: 0.00010698 [environ_conv]: 2.581e-05 [swap_dp_allreduce_reducescatter]: 2.197e-05 [bias_add_comm_swap]: 3.25998e-06 [label_micro_interleaved_index]: 7e-06 [label_fine_grained_interleaved_index]: 3.01999e-06 [merge_cast_opt]: 1.76e-06 [slice_recompute_activation]: 2.27001e-06 [micro_interleaved_order_control]: 2.36998e-06 [assign_add_opt]: 1.50999e-06 [ForceFp32Comm]: 9.30013e-07 [remove_cast_before_assign_add]: 1.07e-06 [full_micro_interleaved_order_control]: 2.44001e-06 [reorder_send_recv_between_fp_bp]: 2.97002e-06 [comm_op_add_attrs]: 1.07e-06 [add_comm_op_reuse_tag]: 9.80013e-07 [interleave_split_concat_branches]: 1.15999e-06 [interleave_parallel_branches]: 1.05999e-06 [overlap_opt_shard_in_pipeline]: 1.21002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.77999e-06 [control_data_broadcast_order]: 4.28e-05 [grouped_pairwise_exchange_alltoall]: 1.69e-06 [offloading_packed_experts]: 1.242e-05 [overlap_recompute_and_grad_model_parallel]: 1.305e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.24e-06 [overlap_recompute_allgather_and_fa_grad]: 1.76e-06 [overlap_recompute_comm]: 2.54001e-06 [overlap_grad_ring_attention]: 1.028e-05 [overlap_grad_flash_sp]: 6.164e-05 [begin_end_overlap_inline]: 5.29981e-07 [split_matmul_comm_elemetwise]: 2.49001e-06 [split_layernorm_comm]: 2.02999e-06 [handle_group_info]: 1.72999e-06 [symbol_engine_optimizer]: 0.00072214, [1] [Cycle 1]: 0.00071472, [6] [build]: 0.0002623 [elim_shapecalc]: 4.168e-05 [elim_not_effective]: 5.985e-05 [opt_reshape]: 0.00020038 [fold_const_symbol]: 9.178e-05 [renormalize]: 6.60017e-07 [detach_backward]: 5.24e-06 [pipeline_parallel_scheduler]: 1.99e-06 [auto_monad_reorder]: 5.681e-05 [get_jit_bprop_graph]: 2.37999e-06 [rewriter_after_jit_bprop_graph]: 7.31001e-06 [opt_after_jit_grad]: 0.00082746 [validate]: 0.00013012 Sums bootstrap : 0.160377s : 6.68% type_inference : 1.724153s : 71.82% event_method : 0.001478s : 0.06% auto_monad : 0.012159s : 0.51% graph_reusing : 0.000117s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000234s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000058s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000293s : 0.01% insert-virtual-dataset : 0.000005s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000238s : 0.01% optimize.rewriter_before_opt_a : 0.000847s : 0.04% optimize.opt_a.expand_dump_flag : 0.000036s : 0.00% optimize.opt_a.switch_simplify : 0.000850s : 0.04% optimize.opt_a.loop_unroll : 0.000290s : 0.01% optimize.opt_a.a_1 : 0.138087s : 5.75% optimize.opt_a.with_stream_mark : 0.000207s : 0.01% optimize.opt_a.recompute_prepare : 0.000082s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000046s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000031s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000031s : 0.00% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.001588s : 0.07% optimize.opt_a.accelerated_algorithm : 0.000110s : 0.00% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000049s : 0.00% optimize.opt_a.shard_inline : 0.000055s : 0.00% optimize.opt_a.merge_send_recv : 0.000047s : 0.00% optimize.opt_a.auto_parallel : 0.000043s : 0.00% optimize.opt_a.parallel : 0.000042s : 0.00% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000030s : 0.00% optimize.opt_a.allreduce_fusion : 0.000029s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000052s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000061s : 0.00% optimize.opt_a.virtual_dataset : 0.000071s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000052s : 0.00% optimize.opt_a.virtual_output : 0.000051s : 0.00% optimize.opt_a.merge_forward : 0.000032s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000054s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000112s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000094s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000084s : 0.00% optimize.opt_a.meta_fg_expand : 0.000043s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000073s : 0.00% optimize.opt_a.a_after_grad : 0.000080s : 0.00% optimize.opt_a.renormalize : 0.349968s : 14.58% optimize.opt_a.add_forward_monad_depend : 0.000028s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000108s : 0.00% optimize.opt_a.cse : 0.000499s : 0.02% optimize.opt_a.a_3 : 0.000351s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000084s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.001063s : 0.04% optimize.convert_after_rewriter : 0.000037s : 0.00% optimize.order_py_execute_after_rewriter : 0.000014s : 0.00% optimize.mutable_eliminate : 0.000934s : 0.04% optimize.opt_b.b_1 : 0.000618s : 0.03% optimize.opt_b.b_2 : 0.000030s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000025s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000138s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000052s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000050s : 0.00% optimize.loop_unroll : 0.000685s : 0.03% optimize.opt_after_cconv.c_1 : 0.000150s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.cse : 0.000105s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000148s : 0.01% optimize.tuple_transform.d_1 : 0.000768s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000005s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000031s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000195s : 0.01% optimize.cse_after_recomputation.cse : 0.000107s : 0.00% optimize.environ_conv : 0.000026s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000022s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000043s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000012s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000013s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000062s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000262s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000042s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000060s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000200s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000092s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000057s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000827s : 0.03% validate : 0.000130s : 0.01% Time group info: ------[substitution.] 0.129510 668 0.05% : 0.000067s : 7: substitution.arithmetic_simplify 0.01% : 0.000011s : 7: substitution.depend_value_elim 0.01% : 0.000015s : 17: substitution.elim_not_effective 0.02% : 0.000023s : 20: substitution.float_tuple_getitem_switch 0.04% : 0.000052s : 13: substitution.fold_const_symbol 0.02% : 0.000023s : 20: substitution.graph_param_transform 98.92% : 0.128111s : 100: substitution.inline 0.01% : 0.000016s : 35: substitution.j_node_and_user_rematch 0.03% : 0.000036s : 7: substitution.less_batch_normalization 0.06% : 0.000079s : 3: substitution.list_to_tuple_eliminator_ 0.02% : 0.000028s : 15: substitution.minmaximum_grad 0.05% : 0.000067s : 6: substitution.opt_reshape 0.02% : 0.000025s : 35: substitution.remove_not_recompute_node 0.01% : 0.000011s : 4: substitution.replace_old_param 0.07% : 0.000094s : 29: substitution.reshape_eliminate 0.04% : 0.000052s : 21: substitution.switch_simplify 0.14% : 0.000175s : 60: substitution.tuple_list_convert_item_index_to_positive 0.07% : 0.000087s : 60: substitution.tuple_list_get_item_const_eliminator 0.10% : 0.000125s : 60: substitution.tuple_list_get_item_depend_reorder 0.22% : 0.000286s : 89: substitution.tuple_list_get_item_eliminator 0.10% : 0.000127s : 60: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.723755 2 86.14% : 1.484787s : 1: type_inference.infer 13.86% : 0.238968s : 1: type_inference.specialize ------[replace.] 0.002370 148 7.38% : 0.000175s : 7: replace.depend_value_elim 67.21% : 0.001593s : 100: replace.inline 2.61% : 0.000062s : 3: replace.list_to_tuple_eliminator_ 3.43% : 0.000081s : 3: replace.opt_reshape 13.62% : 0.000323s : 21: replace.switch_simplify 5.75% : 0.000136s : 14: replace.tuple_list_get_item_eliminator ------[match.] 0.128265 148 0.01% : 0.000007s : 7: match.depend_value_elim 99.83% : 0.128042s : 100: match.inline 0.06% : 0.000076s : 3: match.list_to_tuple_eliminator_ 0.05% : 0.000061s : 3: match.opt_reshape 0.03% : 0.000039s : 21: match.switch_simplify 0.03% : 0.000042s : 14: match.tuple_list_get_item_eliminator ------[predicate.] 0.002232 12477 1.18% : 0.000026s : 169: predicate.accumulaten_eliminater 0.34% : 0.000008s : 19: predicate.ad_related_special_op_eliminate 0.47% : 0.000010s : 69: predicate.addn_check_dump 1.15% : 0.000026s : 169: predicate.addn_zero_filter 1.16% : 0.000026s : 169: predicate.adjust_all_reduce_mul_add 2.32% : 0.000052s : 238: predicate.arithmetic_simplify 1.08% : 0.000024s : 169: predicate.cast_eliminate 0.27% : 0.000006s : 40: predicate.check_bprop_eliminate 0.44% : 0.000010s : 69: predicate.compare_switch_simplify 0.07% : 0.000002s : 20: predicate.const_output_eliminate 0.56% : 0.000013s : 73: predicate.depend_value_elim 1.15% : 0.000026s : 169: predicate.dict_get_item_const_eliminator 1.19% : 0.000027s : 169: predicate.dict_get_item_eliminator 1.11% : 0.000025s : 169: predicate.dict_set_item_eliminator 0.30% : 0.000007s : 39: predicate.dumpgradient_eliminate 0.08% : 0.000002s : 20: predicate.elim_not_effective 0.18% : 0.000004s : 20: predicate.elim_shapecalc_of_broadcastargs 1.32% : 0.000030s : 189: predicate.environ_add_const_eliminate 1.38% : 0.000031s : 189: predicate.environ_get_add_eliminate 1.27% : 0.000028s : 189: predicate.environ_get_depend_swap 1.75% : 0.000039s : 258: predicate.environ_get_eliminate 1.20% : 0.000027s : 189: predicate.environ_get_set_eliminate 2.02% : 0.000045s : 286: predicate.exchange_switch_depend_value 2.82% : 0.000063s : 286: predicate.float_depend_g_call 0.47% : 0.000010s : 69: predicate.float_environ_get_switch 0.73% : 0.000016s : 89: predicate.float_tuple_getitem_switch 0.07% : 0.000002s : 19: predicate.fold_const_symbol 0.31% : 0.000007s : 41: predicate.get_grad_eliminate 0.10% : 0.000002s : 20: predicate.graph_param_transform 0.46% : 0.000010s : 69: predicate.incorporate_call 0.41% : 0.000009s : 69: predicate.incorporate_call_switch 5.66% : 0.000126s : 605: predicate.inline 0.45% : 0.000010s : 41: predicate.inline_without_move 0.13% : 0.000003s : 41: predicate.j_node_and_user_rematch 0.41% : 0.000009s : 41: predicate.less_batch_normalization 1.71% : 0.000038s : 226: predicate.list_to_tuple_eliminator_ 2.58% : 0.000058s : 395: predicate.load_eliminater 0.46% : 0.000010s : 20: predicate.loop_unroll_after_grad 2.60% : 0.000058s : 293: predicate.loop_unroll_before_grad 2.48% : 0.000055s : 209: predicate.make_slice_get_slice_eliminator 0.46% : 0.000010s : 69: predicate.merge_addn 0.25% : 0.000006s : 40: predicate.micro_step_allgather_replace 0.25% : 0.000006s : 40: predicate.mini_step_allgather_replace 1.12% : 0.000025s : 169: predicate.minmaximum_grad 0.46% : 0.000010s : 20: predicate.mutable_eliminate 0.21% : 0.000005s : 25: predicate.opt_reshape 0.14% : 0.000003s : 20: predicate.parallel_virtual_node 3.85% : 0.000086s : 286: predicate.partial_defer_inline 1.46% : 0.000033s : 206: predicate.partial_eliminate 1.07% : 0.000024s : 169: predicate.print_const_string_wrapper 0.50% : 0.000011s : 62: predicate.reduce_all_const_elim 4.91% : 0.000110s : 169: predicate.reduce_eliminate 2.63% : 0.000059s : 395: predicate.redundant_stop_gradient_eliminater 0.15% : 0.000003s : 41: predicate.remove_not_recompute_node 1.05% : 0.000023s : 226: predicate.replace_applicator 0.16% : 0.000004s : 41: predicate.replace_old_param 0.07% : 0.000002s : 20: predicate.reset_defer_inline 1.35% : 0.000030s : 169: predicate.reshape_eliminate 0.25% : 0.000006s : 40: predicate.row_tensor_add_zeros_like 0.17% : 0.000004s : 20: predicate.row_tensor_eliminate 0.33% : 0.000007s : 40: predicate.same_eliminate 0.19% : 0.000004s : 48: predicate.set_cell_output_no_recompute 0.34% : 0.000008s : 41: predicate.shard_identity_eliminate 0.26% : 0.000006s : 39: predicate.special_op_eliminate 0.56% : 0.000012s : 69: predicate.specialize_transform 0.38% : 0.000008s : 40: predicate.split_environ_get_set_with_tuple_value 0.33% : 0.000007s : 41: predicate.stack_unstack_eliminate 0.14% : 0.000003s : 20: predicate.switch_call_monad_eliminater 2.12% : 0.000047s : 286: predicate.switch_defer_inline 2.27% : 0.000051s : 326: predicate.switch_layer_defer_inline 6.45% : 0.000144s : 710: predicate.switch_simplify 1.12% : 0.000025s : 169: predicate.tile_eliminate 1.15% : 0.000026s : 169: predicate.transpose_eliminate 1.73% : 0.000039s : 209: predicate.tuple_list_convert_item_index_to_positive 1.74% : 0.000039s : 209: predicate.tuple_list_get_item_const_eliminator 1.49% : 0.000033s : 209: predicate.tuple_list_get_item_depend_reorder 3.13% : 0.000070s : 292: predicate.tuple_list_get_item_eliminator 1.56% : 0.000035s : 209: predicate.tuple_list_get_set_item_eliminator 2.14% : 0.000048s : 278: predicate.tuple_list_set_item_eliminator 1.46% : 0.000033s : 223: predicate.tuple_to_list_eliminator_ 2.52% : 0.000056s : 395: predicate.updatestate_pure_node_eliminater 3.12% : 0.000070s : 464: predicate.updatestate_useless_node_eliminater 0.15% : 0.000003s : 20: predicate.value_based_eliminate 0.35% : 0.000008s : 41: predicate.virtual_dataset_eliminate 0.32% : 0.000007s : 41: predicate.virtual_output_eliminate 0.14% : 0.000003s : 19: predicate.virtual_view_grad_eliminate 0.15% : 0.000003s : 20: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.511753 137 31.36% : 0.160465s : 45: func_graph_cloner_run.FuncGraphClonerGraph 24.42% : 0.124953s : 17: func_graph_cloner_run.FuncGraphClonerNode 44.23% : 0.226335s : 75: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.746809 209 0.00% : 0.000004s : 1: ForceFp32Comm 4.66% : 0.174416s : 1: add_attr 4.65% : 0.174389s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.01% : 0.000200s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.33% : 0.012198s : 1: auto_monad 0.00% : 0.000062s : 1: auto_monad_reorder 0.00% : 0.000006s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 4.28% : 0.160448s : 1: bootstrap 0.00% : 0.000055s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000047s : 1: control_data_broadcast_order 0.00% : 0.000046s : 1: convert_after_rewriter 0.00% : 0.000133s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000009s : 1: detach_backward 0.00% : 0.000030s : 1: environ_conv 0.04% : 0.001516s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000127s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000006s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.02% : 0.000699s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.000948s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.00% : 0.000054s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000053s : 1: opt.transform.mutable_eliminate 3.79% : 0.141832s : 95: opt.transform.opt_a 0.00% : 0.000149s : 1: opt.transform.opt_after_cconv 0.00% : 0.000082s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000606s : 28: opt.transform.opt_b 0.02% : 0.000792s : 2: opt.transform.opt_trans_graph 0.01% : 0.000387s : 4: opt.transform.symbol_engine_opt 13.19% : 0.494310s : 1: opt_a 0.01% : 0.000366s : 1: opt_after_cconv 0.02% : 0.000843s : 1: opt_after_jit_grad 0.02% : 0.000905s : 1: opt_b 13.40% : 0.502216s : 1: optimize 0.00% : 0.000056s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000065s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000016s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000011s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000007s : 1: pipeline_split 0.01% : 0.000301s : 1: pre_auto_parallel 0.01% : 0.000251s : 1: py_interpret_to_execute 0.00% : 0.000092s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000153s : 1: remove_dup_value 0.48% : 0.017875s : 1: renormalize.infer 8.86% : 0.332068s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.001079s : 1: rewriter_after_opt_a 0.02% : 0.000862s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000026s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000726s : 1: symbol_engine_optimizer 0.02% : 0.000861s : 1: tuple_transform 46.02% : 1.724199s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[True-True-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[True-True-bfloat16--1-shape0],max_mem:116.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:39:51.773.779 [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 = 2.3256, [21] [bootstrap]: 0.00081324 [type_inference]: 1.74279 [event_method]: 0.00024037 [auto_monad]: 0.00074953 [graph_reusing]: 9.04e-05 [inline]: 2.49001e-06 [add_attr]: 0.00629881, [1] [add_attr_with_inline]: 0.0062789, [1] [Cycle 1]: 0.00036715, [2] [tag_attr]: 0.00027005 [meta_addattr_fg_expand]: 4.844e-05 [parallel-infer-symbol]: 5.53997e-06 [pre_auto_parallel]: 0.00032285 [insert-virtual-dataset]: 5.05999e-06 [parallel-infer-symbol-second]: 1.43002e-06 [dataset_repeat_opt]: 2.29999e-06 [pipeline_split]: 2.84999e-06 [optimize]: 0.572915, [53] [py_interpret_to_execute]: 0.00023299 [rewriter_before_opt_a]: 0.00082774 [opt_a]: 0.56523, [2] [Cycle 1]: 0.441845, [45] [expand_dump_flag]: 2.345e-05 [switch_simplify]: 0.00081027 [loop_unroll]: 0.00024968 [a_1]: 0.230371 [with_stream_mark]: 0.00017506 [recompute_prepare]: 5.922e-05 [updatestate_depend_eliminate]: 3.166e-05 [updatestate_assign_eliminate]: 1.879e-05 [updatestate_loads_eliminate]: 1.689e-05 [parameter_eliminate]: 3.19001e-06 [a_2]: 0.00100116 [accelerated_algorithm]: 7.246e-05 [shard]: 3.15998e-06 [meta_shard_fg_expand]: 4.359e-05 [shard_inline]: 2.868e-05 [merge_send_recv]: 2.293e-05 [auto_parallel]: 2.363e-05 [parallel]: 3.418e-05 [flash_sp]: 1.924e-05 [merge_comm]: 1.748e-05 [allreduce_fusion]: 1.45e-05 [matmul_add_comm_reduction]: 2.571e-05 [allreduce_slice_to_reducescatter]: 8.49977e-07 [virtual_shard_identity]: 3.81e-05 [virtual_dataset]: 2.542e-05 [get_grad_eliminate_]: 2.813e-05 [virtual_output]: 2.549e-05 [merge_forward]: 1.574e-05 [cell_reuse_recompute_pass]: 2.12999e-06 [offload_activation]: 2.929e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.767e-05 [merge_recompute_call_nodes]: 2.43e-06 [before_grad]: 5.021e-05 [set_forward_comm_id_for_comm_node_pass]: 1.854e-05 [meta_fg_expand]: 2.737e-05 [flash_sp_send_recv_attached]: 5.19998e-06 [receive_attached]: 2.12001e-06 [after_resolve]: 3.726e-05 [a_after_grad]: 4.099e-05 [renormalize]: 0.207219 [add_forward_monad_depend]: 2.07e-05 [auto_monad_grad]: 3.31999e-06 [auto_monad_eliminator]: 6.362e-05 [cse]: 0.00029651 [a_3]: 0.00018834 [Cycle 2]: 0.123365, [45] [expand_dump_flag]: 3.28998e-06 [switch_simplify]: 2.746e-05 [loop_unroll]: 2.397e-05 [a_1]: 0.12147 [with_stream_mark]: 6.931e-05 [recompute_prepare]: 4.012e-05 [updatestate_depend_eliminate]: 1.8e-05 [updatestate_assign_eliminate]: 1.373e-05 [updatestate_loads_eliminate]: 1.214e-05 [parameter_eliminate]: 3.52997e-06 [a_2]: 0.00039546 [accelerated_algorithm]: 3.613e-05 [shard]: 2.91e-06 [meta_shard_fg_expand]: 1.698e-05 [shard_inline]: 2.438e-05 [merge_send_recv]: 2.435e-05 [auto_parallel]: 2.113e-05 [parallel]: 1.07e-05 [flash_sp]: 8.55999e-06 [merge_comm]: 1.54e-05 [allreduce_fusion]: 1.434e-05 [matmul_add_comm_reduction]: 2.893e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 2.993e-05 [virtual_dataset]: 2.553e-05 [get_grad_eliminate_]: 2.371e-05 [virtual_output]: 2.305e-05 [merge_forward]: 1.615e-05 [cell_reuse_recompute_pass]: 3.03e-06 [offload_activation]: 2.73e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.253e-05 [merge_recompute_call_nodes]: 1.82999e-06 [before_grad]: 4.479e-05 [set_forward_comm_id_for_comm_node_pass]: 2.518e-05 [meta_fg_expand]: 1.407e-05 [flash_sp_send_recv_attached]: 2.01e-06 [receive_attached]: 2.44999e-06 [after_resolve]: 3.262e-05 [a_after_grad]: 4.075e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 6.02999e-06 [auto_monad_grad]: 4.31002e-06 [auto_monad_eliminator]: 5.3e-05 [cse]: 0.00012791 [a_3]: 0.00016788 [py_interpret_to_execute_after_opt_a]: 4.866e-05 [slice_cell_reuse_recomputed_activation]: 2.39001e-06 [rewriter_after_opt_a]: 0.00107395 [convert_after_rewriter]: 4.111e-05 [order_py_execute_after_rewriter]: 1.581e-05 [mutable_eliminate]: 0.00100102 [opt_b]: 0.00091907, [1] [Cycle 1]: 0.00090756, [7] [b_1]: 0.00063084 [b_2]: 3.038e-05 [updatestate_depend_eliminate]: 2.846e-05 [updatestate_assign_eliminate]: 1.288e-05 [updatestate_loads_eliminate]: 1.183e-05 [renormalize]: 1.22e-06 [cse]: 0.00014256 [optimize_parallel_all_gather_comm]: 4.952e-05 [overlap_param_gather]: 2.44999e-06 [cconv]: 4.883e-05 [loop_unroll]: 0.00090582 [opt_after_cconv]: 0.00033924, [1] [Cycle 1]: 0.00032921, [7] [c_1]: 0.00013083 [parameter_eliminate]: 6.07999e-06 [updatestate_depend_eliminate]: 2.439e-05 [updatestate_assign_eliminate]: 1.192e-05 [updatestate_loads_eliminate]: 1.165e-05 [cse]: 0.00010339 [renormalize]: 3.69997e-07 [remove_dup_value]: 0.00014517 [tuple_transform]: 0.00032085, [1] [Cycle 1]: 0.00031316, [4] [d_1]: 0.00026026 [none_parameter_eliminate]: 3.69002e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 2.475e-05 [partial_unused_args_eliminate]: 2.07001e-06 [add_recomputation]: 0.00018105 [cse_after_recomputation]: 7.93e-05, [1] [Cycle 1]: 7.213e-05, [1] [cse]: 6.515e-05 [environ_conv]: 7.05e-05 [swap_dp_allreduce_reducescatter]: 2.177e-05 [bias_add_comm_swap]: 3.08e-06 [label_micro_interleaved_index]: 6.91001e-06 [label_fine_grained_interleaved_index]: 2.69999e-06 [merge_cast_opt]: 1.42e-06 [slice_recompute_activation]: 2.13002e-06 [micro_interleaved_order_control]: 2.88e-06 [assign_add_opt]: 1.22e-06 [ForceFp32Comm]: 1.09e-06 [remove_cast_before_assign_add]: 1.29e-06 [full_micro_interleaved_order_control]: 2.44999e-06 [reorder_send_recv_between_fp_bp]: 3.4e-06 [comm_op_add_attrs]: 1.14998e-06 [add_comm_op_reuse_tag]: 1.01002e-06 [interleave_split_concat_branches]: 1.46002e-06 [interleave_parallel_branches]: 1.08001e-06 [overlap_opt_shard_in_pipeline]: 1.52999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.06998e-06 [control_data_broadcast_order]: 4.411e-05 [grouped_pairwise_exchange_alltoall]: 1.76003e-06 [offloading_packed_experts]: 1.314e-05 [overlap_recompute_and_grad_model_parallel]: 1.36e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.22e-06 [overlap_recompute_allgather_and_fa_grad]: 1.54e-06 [overlap_recompute_comm]: 2.21e-06 [overlap_grad_ring_attention]: 1.107e-05 [overlap_grad_flash_sp]: 5.841e-05 [begin_end_overlap_inline]: 5.60016e-07 [split_matmul_comm_elemetwise]: 3.11001e-06 [split_layernorm_comm]: 1.84e-06 [handle_group_info]: 9.80013e-07 [symbol_engine_optimizer]: 0.00080585, [1] [Cycle 1]: 0.00079919, [6] [build]: 0.00026164 [elim_shapecalc]: 4.359e-05 [elim_not_effective]: 6.016e-05 [opt_reshape]: 0.00029912 [fold_const_symbol]: 6.548e-05 [renormalize]: 8.50006e-07 [detach_backward]: 4.89e-06 [pipeline_parallel_scheduler]: 1.82999e-06 [auto_monad_reorder]: 6.279e-05 [get_jit_bprop_graph]: 2.63e-06 [rewriter_after_jit_bprop_graph]: 8.69e-06 [opt_after_jit_grad]: 0.00090532 [validate]: 0.00011018 Sums bootstrap : 0.000813s : 0.04% type_inference : 1.742788s : 75.19% event_method : 0.000240s : 0.01% auto_monad : 0.000750s : 0.03% graph_reusing : 0.000090s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000270s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000048s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000323s : 0.01% insert-virtual-dataset : 0.000005s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000233s : 0.01% optimize.rewriter_before_opt_a : 0.000828s : 0.04% optimize.opt_a.expand_dump_flag : 0.000027s : 0.00% optimize.opt_a.switch_simplify : 0.000838s : 0.04% optimize.opt_a.loop_unroll : 0.000274s : 0.01% optimize.opt_a.a_1 : 0.351842s : 15.18% optimize.opt_a.with_stream_mark : 0.000244s : 0.01% optimize.opt_a.recompute_prepare : 0.000099s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000050s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000033s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000029s : 0.00% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.001397s : 0.06% optimize.opt_a.accelerated_algorithm : 0.000109s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000061s : 0.00% optimize.opt_a.shard_inline : 0.000053s : 0.00% optimize.opt_a.merge_send_recv : 0.000047s : 0.00% optimize.opt_a.auto_parallel : 0.000045s : 0.00% optimize.opt_a.parallel : 0.000045s : 0.00% optimize.opt_a.flash_sp : 0.000028s : 0.00% optimize.opt_a.merge_comm : 0.000033s : 0.00% optimize.opt_a.allreduce_fusion : 0.000029s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000055s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000068s : 0.00% optimize.opt_a.virtual_dataset : 0.000051s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000052s : 0.00% optimize.opt_a.virtual_output : 0.000049s : 0.00% optimize.opt_a.merge_forward : 0.000032s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000057s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000110s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000095s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000044s : 0.00% optimize.opt_a.meta_fg_expand : 0.000041s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000070s : 0.00% optimize.opt_a.a_after_grad : 0.000082s : 0.00% optimize.opt_a.renormalize : 0.207219s : 8.94% optimize.opt_a.add_forward_monad_depend : 0.000027s : 0.00% optimize.opt_a.auto_monad_grad : 0.000008s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000117s : 0.01% optimize.opt_a.cse : 0.000424s : 0.02% optimize.opt_a.a_3 : 0.000356s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000049s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.001074s : 0.05% optimize.convert_after_rewriter : 0.000041s : 0.00% optimize.order_py_execute_after_rewriter : 0.000016s : 0.00% optimize.mutable_eliminate : 0.001001s : 0.04% optimize.opt_b.b_1 : 0.000631s : 0.03% optimize.opt_b.b_2 : 0.000030s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000028s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000143s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000050s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000049s : 0.00% optimize.loop_unroll : 0.000906s : 0.04% optimize.opt_after_cconv.c_1 : 0.000131s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.cse : 0.000103s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000145s : 0.01% optimize.tuple_transform.d_1 : 0.000260s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000004s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000181s : 0.01% optimize.cse_after_recomputation.cse : 0.000065s : 0.00% optimize.environ_conv : 0.000070s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000022s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000044s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000014s : 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 : 0.000011s : 0.00% optimize.overlap_grad_flash_sp : 0.000058s : 0.00% 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 : 0.000262s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000044s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000060s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000299s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000065s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000063s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000905s : 0.04% validate : 0.000110s : 0.00% Time group info: ------[substitution.] 0.008216 668 0.88% : 0.000073s : 7: substitution.arithmetic_simplify 0.11% : 0.000009s : 7: substitution.depend_value_elim 0.20% : 0.000016s : 17: substitution.elim_not_effective 0.31% : 0.000025s : 20: substitution.float_tuple_getitem_switch 0.34% : 0.000028s : 13: substitution.fold_const_symbol 0.22% : 0.000018s : 20: substitution.graph_param_transform 80.36% : 0.006603s : 100: substitution.inline 0.22% : 0.000018s : 35: substitution.j_node_and_user_rematch 0.43% : 0.000035s : 7: substitution.less_batch_normalization 1.44% : 0.000118s : 3: substitution.list_to_tuple_eliminator_ 0.35% : 0.000029s : 15: substitution.minmaximum_grad 1.79% : 0.000147s : 6: substitution.opt_reshape 0.28% : 0.000023s : 35: substitution.remove_not_recompute_node 0.12% : 0.000010s : 4: substitution.replace_old_param 1.32% : 0.000108s : 29: substitution.reshape_eliminate 0.63% : 0.000052s : 21: substitution.switch_simplify 2.40% : 0.000198s : 60: substitution.tuple_list_convert_item_index_to_positive 1.19% : 0.000098s : 60: substitution.tuple_list_get_item_const_eliminator 1.76% : 0.000145s : 60: substitution.tuple_list_get_item_depend_reorder 3.96% : 0.000325s : 89: substitution.tuple_list_get_item_eliminator 1.69% : 0.000139s : 60: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.742391 2 93.84% : 1.635090s : 1: type_inference.infer 6.16% : 0.107301s : 1: type_inference.specialize ------[replace.] 0.002838 148 2.95% : 0.000084s : 7: replace.depend_value_elim 72.69% : 0.002063s : 100: replace.inline 4.13% : 0.000117s : 3: replace.list_to_tuple_eliminator_ 3.14% : 0.000089s : 3: replace.opt_reshape 11.49% : 0.000326s : 21: replace.switch_simplify 5.61% : 0.000159s : 14: replace.tuple_list_get_item_eliminator ------[match.] 0.006869 148 0.08% : 0.000005s : 7: match.depend_value_elim 94.97% : 0.006524s : 100: match.inline 1.63% : 0.000112s : 3: match.list_to_tuple_eliminator_ 2.03% : 0.000139s : 3: match.opt_reshape 0.55% : 0.000038s : 21: match.switch_simplify 0.74% : 0.000051s : 14: match.tuple_list_get_item_eliminator ------[predicate.] 0.214874 12477 0.01% : 0.000027s : 169: predicate.accumulaten_eliminater 0.00% : 0.000008s : 19: predicate.ad_related_special_op_eliminate 0.00% : 0.000010s : 69: predicate.addn_check_dump 0.01% : 0.000027s : 169: predicate.addn_zero_filter 0.01% : 0.000023s : 169: predicate.adjust_all_reduce_mul_add 0.03% : 0.000055s : 238: predicate.arithmetic_simplify 0.01% : 0.000026s : 169: predicate.cast_eliminate 0.00% : 0.000006s : 40: predicate.check_bprop_eliminate 0.00% : 0.000010s : 69: predicate.compare_switch_simplify 0.00% : 0.000002s : 20: predicate.const_output_eliminate 0.01% : 0.000011s : 73: predicate.depend_value_elim 0.01% : 0.000030s : 169: predicate.dict_get_item_const_eliminator 0.01% : 0.000027s : 169: predicate.dict_get_item_eliminator 0.01% : 0.000030s : 169: predicate.dict_set_item_eliminator 0.00% : 0.000008s : 39: predicate.dumpgradient_eliminate 0.00% : 0.000002s : 20: predicate.elim_not_effective 0.00% : 0.000004s : 20: predicate.elim_shapecalc_of_broadcastargs 0.01% : 0.000030s : 189: predicate.environ_add_const_eliminate 0.01% : 0.000029s : 189: predicate.environ_get_add_eliminate 0.01% : 0.000029s : 189: predicate.environ_get_depend_swap 0.02% : 0.000045s : 258: predicate.environ_get_eliminate 0.01% : 0.000029s : 189: predicate.environ_get_set_eliminate 0.02% : 0.000043s : 286: predicate.exchange_switch_depend_value 0.03% : 0.000067s : 286: predicate.float_depend_g_call 0.01% : 0.000011s : 69: predicate.float_environ_get_switch 0.01% : 0.000015s : 89: predicate.float_tuple_getitem_switch 0.00% : 0.000002s : 19: predicate.fold_const_symbol 0.00% : 0.000007s : 41: predicate.get_grad_eliminate 0.00% : 0.000002s : 20: predicate.graph_param_transform 0.01% : 0.000011s : 69: predicate.incorporate_call 0.00% : 0.000009s : 69: predicate.incorporate_call_switch 0.06% : 0.000136s : 605: predicate.inline 0.00% : 0.000009s : 41: predicate.inline_without_move 0.00% : 0.000003s : 41: predicate.j_node_and_user_rematch 0.00% : 0.000010s : 41: predicate.less_batch_normalization 0.02% : 0.000037s : 226: predicate.list_to_tuple_eliminator_ 0.03% : 0.000056s : 395: predicate.load_eliminater 0.01% : 0.000011s : 20: predicate.loop_unroll_after_grad 0.02% : 0.000053s : 293: predicate.loop_unroll_before_grad 0.01% : 0.000032s : 209: predicate.make_slice_get_slice_eliminator 0.01% : 0.000011s : 69: predicate.merge_addn 0.00% : 0.000006s : 40: predicate.micro_step_allgather_replace 0.00% : 0.000006s : 40: predicate.mini_step_allgather_replace 0.01% : 0.000030s : 169: predicate.minmaximum_grad 0.01% : 0.000014s : 20: predicate.mutable_eliminate 0.00% : 0.000005s : 25: predicate.opt_reshape 0.00% : 0.000003s : 20: predicate.parallel_virtual_node 0.05% : 0.000102s : 286: predicate.partial_defer_inline 0.02% : 0.000033s : 206: predicate.partial_eliminate 0.02% : 0.000035s : 169: predicate.print_const_string_wrapper 0.00% : 0.000010s : 62: predicate.reduce_all_const_elim 0.02% : 0.000038s : 169: predicate.reduce_eliminate 0.03% : 0.000058s : 395: predicate.redundant_stop_gradient_eliminater 0.00% : 0.000003s : 41: predicate.remove_not_recompute_node 0.01% : 0.000023s : 226: predicate.replace_applicator 0.00% : 0.000004s : 41: predicate.replace_old_param 0.00% : 0.000002s : 20: predicate.reset_defer_inline 0.02% : 0.000035s : 169: predicate.reshape_eliminate 0.00% : 0.000006s : 40: predicate.row_tensor_add_zeros_like 0.00% : 0.000004s : 20: predicate.row_tensor_eliminate 0.00% : 0.000008s : 40: predicate.same_eliminate 0.00% : 0.000004s : 48: predicate.set_cell_output_no_recompute 0.00% : 0.000007s : 41: predicate.shard_identity_eliminate 0.00% : 0.000007s : 39: predicate.special_op_eliminate 0.01% : 0.000012s : 69: predicate.specialize_transform 0.00% : 0.000009s : 40: predicate.split_environ_get_set_with_tuple_value 0.00% : 0.000008s : 41: predicate.stack_unstack_eliminate 0.00% : 0.000003s : 20: predicate.switch_call_monad_eliminater 0.02% : 0.000047s : 286: predicate.switch_defer_inline 0.02% : 0.000053s : 326: predicate.switch_layer_defer_inline 0.06% : 0.000131s : 710: predicate.switch_simplify 0.01% : 0.000026s : 169: predicate.tile_eliminate 98.98% : 0.212685s : 169: predicate.transpose_eliminate 0.02% : 0.000039s : 209: predicate.tuple_list_convert_item_index_to_positive 0.02% : 0.000041s : 209: predicate.tuple_list_get_item_const_eliminator 0.02% : 0.000034s : 209: predicate.tuple_list_get_item_depend_reorder 0.03% : 0.000074s : 292: predicate.tuple_list_get_item_eliminator 0.02% : 0.000040s : 209: predicate.tuple_list_get_set_item_eliminator 0.03% : 0.000054s : 278: predicate.tuple_list_set_item_eliminator 0.02% : 0.000034s : 223: predicate.tuple_to_list_eliminator_ 0.03% : 0.000056s : 395: predicate.updatestate_pure_node_eliminater 0.03% : 0.000072s : 464: predicate.updatestate_useless_node_eliminater 0.00% : 0.000003s : 20: predicate.value_based_eliminate 0.00% : 0.000007s : 41: predicate.virtual_dataset_eliminate 0.00% : 0.000007s : 41: predicate.virtual_output_eliminate 0.00% : 0.000003s : 19: predicate.virtual_view_grad_eliminate 0.00% : 0.000003s : 20: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.015576 137 48.04% : 0.007482s : 45: func_graph_cloner_run.FuncGraphClonerGraph 16.93% : 0.002638s : 17: func_graph_cloner_run.FuncGraphClonerNode 35.03% : 0.005456s : 75: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.469024 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.18% : 0.006306s : 1: add_attr 0.18% : 0.006284s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.01% : 0.000188s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000765s : 1: auto_monad 0.00% : 0.000069s : 1: auto_monad_reorder 0.00% : 0.000006s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.03% : 0.000887s : 1: bootstrap 0.00% : 0.000054s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000048s : 1: control_data_broadcast_order 0.00% : 0.000048s : 1: convert_after_rewriter 0.00% : 0.000082s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000076s : 1: environ_conv 0.01% : 0.000251s : 1: event_method 0.00% : 0.000008s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000098s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.03% : 0.000923s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.001021s : 1: mutable_eliminate 0.00% : 0.000017s : 1: offloading_packed_experts 0.01% : 0.000280s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000063s : 1: opt.transform.mutable_eliminate 10.24% : 0.355358s : 95: opt.transform.opt_a 0.00% : 0.000129s : 1: opt.transform.opt_after_cconv 0.00% : 0.000091s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000617s : 28: opt.transform.opt_b 0.01% : 0.000282s : 2: opt.transform.opt_trans_graph 0.01% : 0.000460s : 4: opt.transform.symbol_engine_opt 16.29% : 0.565235s : 1: opt_a 0.01% : 0.000344s : 1: opt_after_cconv 0.03% : 0.000922s : 1: opt_after_jit_grad 0.03% : 0.000925s : 1: opt_b 16.52% : 0.572922s : 1: optimize 0.00% : 0.000056s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000063s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000014s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000017s : 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% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.01% : 0.000333s : 1: pre_auto_parallel 0.01% : 0.000247s : 1: py_interpret_to_execute 0.00% : 0.000055s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000151s : 1: remove_dup_value 5.82% : 0.202048s : 1: renormalize.infer 0.15% : 0.005149s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.001092s : 1: rewriter_after_opt_a 0.02% : 0.000839s : 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% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000025s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000810s : 1: symbol_engine_optimizer 0.01% : 0.000324s : 1: tuple_transform 50.24% : 1.742813s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[True-True-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[True-True-bfloat16--1-shape1],max_mem:120.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:40:01.525.211 [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 = 3.66763, [21] [bootstrap]: 0.00070672 [type_inference]: 2.22139 [event_method]: 0.00021137 [auto_monad]: 0.00060581 [graph_reusing]: 7.044e-05 [inline]: 2.69999e-06 [add_attr]: 0.596503, [1] [add_attr_with_inline]: 0.596225, [1] [Cycle 1]: 0.00032989, [2] [tag_attr]: 0.00023154 [meta_addattr_fg_expand]: 4.775e-05 [parallel-infer-symbol]: 5.64e-06 [pre_auto_parallel]: 0.00036198 [insert-virtual-dataset]: 4.52e-06 [parallel-infer-symbol-second]: 9.79984e-07 [dataset_repeat_opt]: 2.31e-06 [pipeline_split]: 3.23998e-06 [optimize]: 0.846722, [53] [py_interpret_to_execute]: 0.00023971 [rewriter_before_opt_a]: 0.00081268 [opt_a]: 0.481969, [2] [Cycle 1]: 0.479575, [45] [expand_dump_flag]: 2.389e-05 [switch_simplify]: 0.00374007 [loop_unroll]: 0.00060746 [a_1]: 0.267092 [with_stream_mark]: 0.00015424 [recompute_prepare]: 5.2e-05 [updatestate_depend_eliminate]: 3.043e-05 [updatestate_assign_eliminate]: 1.818e-05 [updatestate_loads_eliminate]: 1.671e-05 [parameter_eliminate]: 2.93998e-06 [a_2]: 0.00129317 [accelerated_algorithm]: 7.072e-05 [shard]: 2.98e-06 [meta_shard_fg_expand]: 3.48e-05 [shard_inline]: 2.884e-05 [merge_send_recv]: 2.369e-05 [auto_parallel]: 2.274e-05 [parallel]: 0.00052558 [flash_sp]: 2.442e-05 [merge_comm]: 2.033e-05 [allreduce_fusion]: 1.418e-05 [matmul_add_comm_reduction]: 2.408e-05 [allreduce_slice_to_reducescatter]: 1.09e-06 [virtual_shard_identity]: 3.742e-05 [virtual_dataset]: 2.553e-05 [get_grad_eliminate_]: 2.586e-05 [virtual_output]: 2.508e-05 [merge_forward]: 1.388e-05 [cell_reuse_recompute_pass]: 2.32001e-06 [offload_activation]: 2.589e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.699e-05 [merge_recompute_call_nodes]: 1.40999e-06 [before_grad]: 4.878e-05 [set_forward_comm_id_for_comm_node_pass]: 1.649e-05 [meta_fg_expand]: 2.505e-05 [flash_sp_send_recv_attached]: 6.38e-06 [receive_attached]: 1.96003e-06 [after_resolve]: 3.443e-05 [a_after_grad]: 4.133e-05 [renormalize]: 0.20402 [add_forward_monad_depend]: 0.00027636 [auto_monad_grad]: 2.97002e-06 [auto_monad_eliminator]: 6.249e-05 [cse]: 0.00033161 [a_3]: 0.00018989 [Cycle 2]: 0.0023762, [45] [expand_dump_flag]: 2.91999e-06 [switch_simplify]: 2.619e-05 [loop_unroll]: 2.433e-05 [a_1]: 0.00084974 [with_stream_mark]: 3.107e-05 [recompute_prepare]: 2.376e-05 [updatestate_depend_eliminate]: 1.476e-05 [updatestate_assign_eliminate]: 1.213e-05 [updatestate_loads_eliminate]: 1.22e-05 [parameter_eliminate]: 2.69001e-06 [a_2]: 0.00035777 [accelerated_algorithm]: 3.366e-05 [shard]: 2.49001e-06 [meta_shard_fg_expand]: 6.88e-06 [shard_inline]: 2.395e-05 [merge_send_recv]: 2.12e-05 [auto_parallel]: 2.079e-05 [parallel]: 1.019e-05 [flash_sp]: 4.4e-06 [merge_comm]: 1.436e-05 [allreduce_fusion]: 1.331e-05 [matmul_add_comm_reduction]: 2.347e-05 [allreduce_slice_to_reducescatter]: 1.12e-06 [virtual_shard_identity]: 2.554e-05 [virtual_dataset]: 3.772e-05 [get_grad_eliminate_]: 2.328e-05 [virtual_output]: 2.309e-05 [merge_forward]: 1.609e-05 [cell_reuse_recompute_pass]: 3.31001e-06 [offload_activation]: 2.357e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.856e-05 [merge_recompute_call_nodes]: 1.72001e-06 [before_grad]: 4.029e-05 [set_forward_comm_id_for_comm_node_pass]: 1.477e-05 [meta_fg_expand]: 1.076e-05 [flash_sp_send_recv_attached]: 2.63e-06 [receive_attached]: 2.63e-06 [after_resolve]: 3.095e-05 [a_after_grad]: 3.623e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.31998e-06 [auto_monad_grad]: 1.86e-06 [auto_monad_eliminator]: 2.945e-05 [cse]: 7.866e-05 [a_3]: 0.00015459 [py_interpret_to_execute_after_opt_a]: 3.711e-05 [slice_cell_reuse_recomputed_activation]: 1.96003e-06 [rewriter_after_opt_a]: 0.357894 [convert_after_rewriter]: 5.547e-05 [order_py_execute_after_rewriter]: 1.636e-05 [mutable_eliminate]: 0.00096094 [opt_b]: 0.00088075, [1] [Cycle 1]: 0.00087164, [7] [b_1]: 0.00062035 [b_2]: 2.799e-05 [updatestate_depend_eliminate]: 2.003e-05 [updatestate_assign_eliminate]: 1.241e-05 [updatestate_loads_eliminate]: 1.307e-05 [renormalize]: 7.29982e-07 [cse]: 0.00013357 [optimize_parallel_all_gather_comm]: 4.69e-05 [overlap_param_gather]: 2.19999e-06 [cconv]: 4.316e-05 [loop_unroll]: 0.00049595 [opt_after_cconv]: 0.00028833, [1] [Cycle 1]: 0.00028032, [7] [c_1]: 0.00012198 [parameter_eliminate]: 3.88999e-06 [updatestate_depend_eliminate]: 1.73e-05 [updatestate_assign_eliminate]: 1.103e-05 [updatestate_loads_eliminate]: 1.063e-05 [cse]: 7.743e-05 [renormalize]: 4.50003e-07 [remove_dup_value]: 0.00013875 [tuple_transform]: 0.00028569, [1] [Cycle 1]: 0.00027851, [4] [d_1]: 0.00022996 [none_parameter_eliminate]: 2.06998e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 2.528e-05 [partial_unused_args_eliminate]: 1.93002e-06 [add_recomputation]: 0.00030463 [cse_after_recomputation]: 7.38e-05, [1] [Cycle 1]: 6.635e-05, [1] [cse]: 6.008e-05 [environ_conv]: 2.34e-05 [swap_dp_allreduce_reducescatter]: 2.043e-05 [bias_add_comm_swap]: 2.76e-06 [label_micro_interleaved_index]: 4.23001e-06 [label_fine_grained_interleaved_index]: 2.83e-06 [merge_cast_opt]: 1.34e-06 [slice_recompute_activation]: 2.10002e-06 [micro_interleaved_order_control]: 2.48e-06 [assign_add_opt]: 1.19e-06 [ForceFp32Comm]: 1.37e-06 [remove_cast_before_assign_add]: 1.10999e-06 [full_micro_interleaved_order_control]: 2.15002e-06 [reorder_send_recv_between_fp_bp]: 2.90002e-06 [comm_op_add_attrs]: 1.02998e-06 [add_comm_op_reuse_tag]: 9.39996e-07 [interleave_split_concat_branches]: 1.23002e-06 [interleave_parallel_branches]: 1.07998e-06 [overlap_opt_shard_in_pipeline]: 1.37e-06 [overlap_opt_shard_grad_in_pipeline]: 1.79e-06 [control_data_broadcast_order]: 3.922e-05 [grouped_pairwise_exchange_alltoall]: 1.49e-06 [offloading_packed_experts]: 1.232e-05 [overlap_recompute_and_grad_model_parallel]: 1.199e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.17999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.22e-06 [overlap_recompute_comm]: 2.06998e-06 [overlap_grad_ring_attention]: 9.54e-06 [overlap_grad_flash_sp]: 5.57e-05 [begin_end_overlap_inline]: 5.79981e-07 [split_matmul_comm_elemetwise]: 2.11e-06 [split_layernorm_comm]: 1.82999e-06 [handle_group_info]: 1.01002e-06 [symbol_engine_optimizer]: 0.00131928, [1] [Cycle 1]: 0.00131307, [6] [build]: 0.00035508 [elim_shapecalc]: 0.00021395 [elim_not_effective]: 5.452e-05 [opt_reshape]: 0.00039464 [fold_const_symbol]: 6.193e-05 [renormalize]: 6.19999e-07 [detach_backward]: 4.40999e-06 [pipeline_parallel_scheduler]: 1.54e-06 [auto_monad_reorder]: 5.022e-05 [get_jit_bprop_graph]: 2.08002e-06 [rewriter_after_jit_bprop_graph]: 6.15002e-06 [opt_after_jit_grad]: 0.00062901 [validate]: 9.289e-05 Sums bootstrap : 0.000707s : 0.02% type_inference : 2.221389s : 72.37% event_method : 0.000211s : 0.01% auto_monad : 0.000606s : 0.02% graph_reusing : 0.000070s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000232s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000048s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000362s : 0.01% insert-virtual-dataset : 0.000005s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000240s : 0.01% optimize.rewriter_before_opt_a : 0.000813s : 0.03% optimize.opt_a.expand_dump_flag : 0.000027s : 0.00% optimize.opt_a.switch_simplify : 0.003766s : 0.12% optimize.opt_a.loop_unroll : 0.000632s : 0.02% optimize.opt_a.a_1 : 0.267942s : 8.73% optimize.opt_a.with_stream_mark : 0.000185s : 0.01% optimize.opt_a.recompute_prepare : 0.000076s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000045s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000030s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000029s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001651s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000104s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000042s : 0.00% optimize.opt_a.shard_inline : 0.000053s : 0.00% optimize.opt_a.merge_send_recv : 0.000045s : 0.00% optimize.opt_a.auto_parallel : 0.000044s : 0.00% optimize.opt_a.parallel : 0.000536s : 0.02% optimize.opt_a.flash_sp : 0.000029s : 0.00% optimize.opt_a.merge_comm : 0.000035s : 0.00% optimize.opt_a.allreduce_fusion : 0.000027s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000048s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000063s : 0.00% optimize.opt_a.virtual_dataset : 0.000063s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000049s : 0.00% optimize.opt_a.virtual_output : 0.000048s : 0.00% optimize.opt_a.merge_forward : 0.000030s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000049s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000106s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000089s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000031s : 0.00% optimize.opt_a.meta_fg_expand : 0.000036s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000065s : 0.00% optimize.opt_a.a_after_grad : 0.000078s : 0.00% optimize.opt_a.renormalize : 0.204020s : 6.65% optimize.opt_a.add_forward_monad_depend : 0.000279s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000092s : 0.00% optimize.opt_a.cse : 0.000410s : 0.01% optimize.opt_a.a_3 : 0.000344s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000037s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.357894s : 11.66% optimize.convert_after_rewriter : 0.000055s : 0.00% optimize.order_py_execute_after_rewriter : 0.000016s : 0.00% optimize.mutable_eliminate : 0.000961s : 0.03% optimize.opt_b.b_1 : 0.000620s : 0.02% optimize.opt_b.b_2 : 0.000028s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000134s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000047s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000043s : 0.00% optimize.loop_unroll : 0.000496s : 0.02% optimize.opt_after_cconv.c_1 : 0.000122s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.cse : 0.000077s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000139s : 0.00% optimize.tuple_transform.d_1 : 0.000230s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000305s : 0.01% optimize.cse_after_recomputation.cse : 0.000060s : 0.00% optimize.environ_conv : 0.000023s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000020s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000004s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000039s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000012s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000056s : 0.00% 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 : 0.000355s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000214s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000055s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000395s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000062s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000050s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000629s : 0.02% validate : 0.000093s : 0.00% Time group info: ------[substitution.] 0.258125 668 0.02% : 0.000063s : 7: substitution.arithmetic_simplify 0.00% : 0.000009s : 7: substitution.depend_value_elim 0.01% : 0.000014s : 17: substitution.elim_not_effective 0.01% : 0.000023s : 20: substitution.float_tuple_getitem_switch 0.01% : 0.000026s : 13: substitution.fold_const_symbol 0.01% : 0.000016s : 20: substitution.graph_param_transform 99.37% : 0.256509s : 100: substitution.inline 0.01% : 0.000016s : 35: substitution.j_node_and_user_rematch 0.01% : 0.000034s : 7: substitution.less_batch_normalization 0.03% : 0.000088s : 3: substitution.list_to_tuple_eliminator_ 0.01% : 0.000027s : 15: substitution.minmaximum_grad 0.02% : 0.000064s : 6: substitution.opt_reshape 0.01% : 0.000023s : 35: substitution.remove_not_recompute_node 0.00% : 0.000010s : 4: substitution.replace_old_param 0.03% : 0.000072s : 29: substitution.reshape_eliminate 0.02% : 0.000063s : 21: substitution.switch_simplify 0.07% : 0.000170s : 60: substitution.tuple_list_convert_item_index_to_positive 0.04% : 0.000091s : 60: substitution.tuple_list_get_item_const_eliminator 0.05% : 0.000134s : 60: substitution.tuple_list_get_item_depend_reorder 0.20% : 0.000526s : 89: substitution.tuple_list_get_item_eliminator 0.06% : 0.000147s : 60: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.220931 2 87.23% : 1.937311s : 1: type_inference.infer 12.77% : 0.283620s : 1: type_inference.specialize ------[replace.] 0.003072 148 9.69% : 0.000298s : 7: replace.depend_value_elim 58.55% : 0.001799s : 100: replace.inline 2.44% : 0.000075s : 3: replace.list_to_tuple_eliminator_ 9.05% : 0.000278s : 3: replace.opt_reshape 15.74% : 0.000484s : 21: replace.switch_simplify 4.52% : 0.000139s : 14: replace.tuple_list_get_item_eliminator ------[match.] 0.256682 148 0.00% : 0.000006s : 7: match.depend_value_elim 99.91% : 0.256441s : 100: match.inline 0.03% : 0.000084s : 3: match.list_to_tuple_eliminator_ 0.02% : 0.000058s : 3: match.opt_reshape 0.02% : 0.000050s : 21: match.switch_simplify 0.02% : 0.000043s : 14: match.tuple_list_get_item_eliminator ------[predicate.] 0.004936 12477 0.51% : 0.000025s : 169: predicate.accumulaten_eliminater 0.11% : 0.000005s : 19: predicate.ad_related_special_op_eliminate 0.21% : 0.000010s : 69: predicate.addn_check_dump 0.52% : 0.000025s : 169: predicate.addn_zero_filter 0.50% : 0.000025s : 169: predicate.adjust_all_reduce_mul_add 0.96% : 0.000048s : 238: predicate.arithmetic_simplify 0.68% : 0.000034s : 169: predicate.cast_eliminate 0.13% : 0.000007s : 40: predicate.check_bprop_eliminate 0.20% : 0.000010s : 69: predicate.compare_switch_simplify 0.03% : 0.000002s : 20: predicate.const_output_eliminate 0.24% : 0.000012s : 73: predicate.depend_value_elim 0.54% : 0.000027s : 169: predicate.dict_get_item_const_eliminator 0.55% : 0.000027s : 169: predicate.dict_get_item_eliminator 0.65% : 0.000032s : 169: predicate.dict_set_item_eliminator 0.13% : 0.000007s : 39: predicate.dumpgradient_eliminate 0.03% : 0.000002s : 20: predicate.elim_not_effective 3.66% : 0.000181s : 20: predicate.elim_shapecalc_of_broadcastargs 0.56% : 0.000028s : 189: predicate.environ_add_const_eliminate 0.59% : 0.000029s : 189: predicate.environ_get_add_eliminate 0.55% : 0.000027s : 189: predicate.environ_get_depend_swap 0.82% : 0.000041s : 258: predicate.environ_get_eliminate 0.55% : 0.000027s : 189: predicate.environ_get_set_eliminate 0.87% : 0.000043s : 286: predicate.exchange_switch_depend_value 1.22% : 0.000060s : 286: predicate.float_depend_g_call 0.20% : 0.000010s : 69: predicate.float_environ_get_switch 0.32% : 0.000016s : 89: predicate.float_tuple_getitem_switch 0.03% : 0.000002s : 19: predicate.fold_const_symbol 0.13% : 0.000006s : 41: predicate.get_grad_eliminate 0.04% : 0.000002s : 20: predicate.graph_param_transform 0.20% : 0.000010s : 69: predicate.incorporate_call 0.18% : 0.000009s : 69: predicate.incorporate_call_switch 2.59% : 0.000128s : 605: predicate.inline 0.18% : 0.000009s : 41: predicate.inline_without_move 0.06% : 0.000003s : 41: predicate.j_node_and_user_rematch 0.19% : 0.000009s : 41: predicate.less_batch_normalization 2.13% : 0.000105s : 226: predicate.list_to_tuple_eliminator_ 1.11% : 0.000055s : 395: predicate.load_eliminater 0.13% : 0.000006s : 20: predicate.loop_unroll_after_grad 1.38% : 0.000068s : 293: predicate.loop_unroll_before_grad 0.68% : 0.000034s : 209: predicate.make_slice_get_slice_eliminator 0.21% : 0.000010s : 69: predicate.merge_addn 0.11% : 0.000005s : 40: predicate.micro_step_allgather_replace 0.11% : 0.000005s : 40: predicate.mini_step_allgather_replace 0.50% : 0.000025s : 169: predicate.minmaximum_grad 0.15% : 0.000008s : 20: predicate.mutable_eliminate 0.09% : 0.000004s : 25: predicate.opt_reshape 0.07% : 0.000003s : 20: predicate.parallel_virtual_node 1.71% : 0.000084s : 286: predicate.partial_defer_inline 0.67% : 0.000033s : 206: predicate.partial_eliminate 0.48% : 0.000023s : 169: predicate.print_const_string_wrapper 0.20% : 0.000010s : 62: predicate.reduce_all_const_elim 0.68% : 0.000033s : 169: predicate.reduce_eliminate 1.13% : 0.000056s : 395: predicate.redundant_stop_gradient_eliminater 0.08% : 0.000004s : 41: predicate.remove_not_recompute_node 0.54% : 0.000027s : 226: predicate.replace_applicator 0.06% : 0.000003s : 41: predicate.replace_old_param 0.04% : 0.000002s : 20: predicate.reset_defer_inline 0.53% : 0.000026s : 169: predicate.reshape_eliminate 0.13% : 0.000007s : 40: predicate.row_tensor_add_zeros_like 0.07% : 0.000003s : 20: predicate.row_tensor_eliminate 0.15% : 0.000007s : 40: predicate.same_eliminate 0.09% : 0.000004s : 48: predicate.set_cell_output_no_recompute 0.14% : 0.000007s : 41: predicate.shard_identity_eliminate 0.12% : 0.000006s : 39: predicate.special_op_eliminate 0.24% : 0.000012s : 69: predicate.specialize_transform 0.15% : 0.000007s : 40: predicate.split_environ_get_set_with_tuple_value 0.14% : 0.000007s : 41: predicate.stack_unstack_eliminate 0.06% : 0.000003s : 20: predicate.switch_call_monad_eliminater 1.00% : 0.000050s : 286: predicate.switch_defer_inline 1.02% : 0.000050s : 326: predicate.switch_layer_defer_inline 54.69% : 0.002699s : 710: predicate.switch_simplify 0.49% : 0.000024s : 169: predicate.tile_eliminate 0.53% : 0.000026s : 169: predicate.transpose_eliminate 0.95% : 0.000047s : 209: predicate.tuple_list_convert_item_index_to_positive 1.09% : 0.000054s : 209: predicate.tuple_list_get_item_const_eliminator 0.65% : 0.000032s : 209: predicate.tuple_list_get_item_depend_reorder 1.33% : 0.000066s : 292: predicate.tuple_list_get_item_eliminator 0.67% : 0.000033s : 209: predicate.tuple_list_get_set_item_eliminator 0.96% : 0.000047s : 278: predicate.tuple_list_set_item_eliminator 0.65% : 0.000032s : 223: predicate.tuple_to_list_eliminator_ 1.11% : 0.000055s : 395: predicate.updatestate_pure_node_eliminater 1.35% : 0.000067s : 464: predicate.updatestate_useless_node_eliminater 0.06% : 0.000003s : 20: predicate.value_based_eliminate 0.14% : 0.000007s : 41: predicate.virtual_dataset_eliminate 0.14% : 0.000007s : 41: predicate.virtual_output_eliminate 0.06% : 0.000003s : 19: predicate.virtual_view_grad_eliminate 0.07% : 0.000003s : 20: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.474078 137 46.88% : 0.222235s : 45: func_graph_cloner_run.FuncGraphClonerGraph 0.44% : 0.002107s : 17: func_graph_cloner_run.FuncGraphClonerNode 52.68% : 0.249736s : 75: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 5.590876 209 0.00% : 0.000004s : 1: ForceFp32Comm 10.67% : 0.596510s : 1: add_attr 10.66% : 0.596231s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.01% : 0.000311s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000623s : 1: auto_monad 0.00% : 0.000055s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.01% : 0.000766s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000043s : 1: control_data_broadcast_order 0.00% : 0.000063s : 1: convert_after_rewriter 0.00% : 0.000077s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000027s : 1: environ_conv 0.00% : 0.000223s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000078s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000007s : 1: label_micro_interleaved_index 0.01% : 0.000505s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000972s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.00% : 0.000037s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000049s : 1: opt.transform.mutable_eliminate 4.92% : 0.274970s : 95: opt.transform.opt_a 0.00% : 0.000121s : 1: opt.transform.opt_after_cconv 0.00% : 0.000076s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000607s : 28: opt.transform.opt_b 0.00% : 0.000252s : 2: opt.transform.opt_trans_graph 0.01% : 0.000718s : 4: opt.transform.symbol_engine_opt 8.62% : 0.481974s : 1: opt_a 0.01% : 0.000292s : 1: opt_after_cconv 0.01% : 0.000640s : 1: opt_after_jit_grad 0.02% : 0.000885s : 1: opt_b 15.14% : 0.846729s : 1: optimize 0.00% : 0.000051s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000020s : 1: order_py_execute_after_rewriter 0.00% : 0.000059s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 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% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.01% : 0.000369s : 1: pre_auto_parallel 0.00% : 0.000254s : 1: py_interpret_to_execute 0.00% : 0.000042s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000144s : 1: remove_dup_value 3.37% : 0.188644s : 1: renormalize.infer 0.27% : 0.015355s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 6.40% : 0.357921s : 1: rewriter_after_opt_a 0.01% : 0.000824s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000024s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.001323s : 1: symbol_engine_optimizer 0.01% : 0.000289s : 1: tuple_transform 39.73% : 2.221434s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[True-True-bfloat16--1-shape2] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[True-True-bfloat16--1-shape2],max_mem:120.0M [WARNING] ME(170207:281473663500080,MainProcess):2026-01-29-17:40:11.382.998 [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 = 2.17958, [21] [bootstrap]: 0.00069335 [type_inference]: 1.56003 [event_method]: 0.00037092 [auto_monad]: 0.00102485 [graph_reusing]: 0.00010144 [inline]: 2.57001e-06 [add_attr]: 0.121196, [1] [add_attr_with_inline]: 0.121173, [1] [Cycle 1]: 0.00041225, [2] [tag_attr]: 0.00028114 [meta_addattr_fg_expand]: 7.533e-05 [parallel-infer-symbol]: 5.67999e-06 [pre_auto_parallel]: 0.00046459 [insert-virtual-dataset]: 5.50001e-06 [parallel-infer-symbol-second]: 2.17999e-06 [dataset_repeat_opt]: 2.39001e-06 [pipeline_split]: 2.93e-06 [optimize]: 0.354738, [53] [py_interpret_to_execute]: 0.00030504 [rewriter_before_opt_a]: 0.00097878 [opt_a]: 0.331868, [2] [Cycle 1]: 0.329015, [45] [expand_dump_flag]: 4.067e-05 [switch_simplify]: 0.00110726 [loop_unroll]: 0.00033019 [a_1]: 0.165085 [with_stream_mark]: 0.0002058 [recompute_prepare]: 6.45e-05 [updatestate_depend_eliminate]: 3.385e-05 [updatestate_assign_eliminate]: 2.018e-05 [updatestate_loads_eliminate]: 1.775e-05 [parameter_eliminate]: 4.4e-06 [a_2]: 0.00164071 [accelerated_algorithm]: 9.966e-05 [shard]: 2.98e-06 [meta_shard_fg_expand]: 5.207e-05 [shard_inline]: 4.022e-05 [merge_send_recv]: 2.825e-05 [auto_parallel]: 2.601e-05 [parallel]: 3.656e-05 [flash_sp]: 1.994e-05 [merge_comm]: 1.693e-05 [allreduce_fusion]: 1.68e-05 [matmul_add_comm_reduction]: 2.76e-05 [allreduce_slice_to_reducescatter]: 9.89996e-07 [virtual_shard_identity]: 3.992e-05 [virtual_dataset]: 2.718e-05 [get_grad_eliminate_]: 2.964e-05 [virtual_output]: 2.865e-05 [merge_forward]: 1.683e-05 [cell_reuse_recompute_pass]: 3.16999e-06 [offload_activation]: 3.196e-05 [cell_reuse_handle_not_recompute_node_pass]: 6.837e-05 [merge_recompute_call_nodes]: 2.03002e-06 [before_grad]: 5.53e-05 [set_forward_comm_id_for_comm_node_pass]: 2.264e-05 [meta_fg_expand]: 4.015e-05 [flash_sp_send_recv_attached]: 6.67002e-06 [receive_attached]: 2.88e-06 [after_resolve]: 4.786e-05 [a_after_grad]: 4.457e-05 [renormalize]: 0.158356 [add_forward_monad_depend]: 2.373e-05 [auto_monad_grad]: 3.11999e-06 [auto_monad_eliminator]: 7.844e-05 [cse]: 0.00033624 [a_3]: 0.00023898 [Cycle 2]: 0.00282928, [45] [expand_dump_flag]: 4.18999e-06 [switch_simplify]: 3.192e-05 [loop_unroll]: 2.693e-05 [a_1]: 0.00082183 [with_stream_mark]: 4.768e-05 [recompute_prepare]: 3.727e-05 [updatestate_depend_eliminate]: 1.802e-05 [updatestate_assign_eliminate]: 1.227e-05 [updatestate_loads_eliminate]: 1.225e-05 [parameter_eliminate]: 2.84999e-06 [a_2]: 0.00039113 [accelerated_algorithm]: 4.416e-05 [shard]: 2.96999e-06 [meta_shard_fg_expand]: 1.451e-05 [shard_inline]: 2.727e-05 [merge_send_recv]: 2.796e-05 [auto_parallel]: 2.298e-05 [parallel]: 1.232e-05 [flash_sp]: 7.35e-06 [merge_comm]: 1.901e-05 [allreduce_fusion]: 1.442e-05 [matmul_add_comm_reduction]: 3.103e-05 [allreduce_slice_to_reducescatter]: 1.02998e-06 [virtual_shard_identity]: 3.69e-05 [virtual_dataset]: 2.706e-05 [get_grad_eliminate_]: 2.545e-05 [virtual_output]: 4.486e-05 [merge_forward]: 2.514e-05 [cell_reuse_recompute_pass]: 4.82998e-06 [offload_activation]: 3.436e-05 [cell_reuse_handle_not_recompute_node_pass]: 6.736e-05 [merge_recompute_call_nodes]: 2.24999e-06 [before_grad]: 5.007e-05 [set_forward_comm_id_for_comm_node_pass]: 2.108e-05 [meta_fg_expand]: 1.441e-05 [flash_sp_send_recv_attached]: 2.37999e-06 [receive_attached]: 2.68e-06 [after_resolve]: 3.805e-05 [a_after_grad]: 4.137e-05 [renormalize]: 6.00121e-08 [add_forward_monad_depend]: 7.21999e-06 [auto_monad_grad]: 3.45e-06 [auto_monad_eliminator]: 4.99e-05 [cse]: 0.00012576 [a_3]: 0.00017851 [py_interpret_to_execute_after_opt_a]: 5.069e-05 [slice_cell_reuse_recomputed_activation]: 2.97002e-06 [rewriter_after_opt_a]: 0.00128561 [convert_after_rewriter]: 5.142e-05 [order_py_execute_after_rewriter]: 1.605e-05 [mutable_eliminate]: 0.00101764 [opt_b]: 0.00105262, [1] [Cycle 1]: 0.00104051, [7] [b_1]: 0.0006926 [b_2]: 3.54e-05 [updatestate_depend_eliminate]: 3.166e-05 [updatestate_assign_eliminate]: 1.429e-05 [updatestate_loads_eliminate]: 1.288e-05 [renormalize]: 9.50007e-07 [cse]: 0.0001777 [optimize_parallel_all_gather_comm]: 0.00038763 [overlap_param_gather]: 4.77e-06 [cconv]: 5.554e-05 [loop_unroll]: 0.00093192 [opt_after_cconv]: 0.00036705, [1] [Cycle 1]: 0.0003571, [7] [c_1]: 0.00013347 [parameter_eliminate]: 7.5e-06 [updatestate_depend_eliminate]: 2.742e-05 [updatestate_assign_eliminate]: 1.255e-05 [updatestate_loads_eliminate]: 1.188e-05 [cse]: 0.00012365 [renormalize]: 7.30011e-07 [remove_dup_value]: 0.00018419 [tuple_transform]: 0.00034965, [1] [Cycle 1]: 0.00033911, [4] [d_1]: 0.00027697 [none_parameter_eliminate]: 3.76999e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 2.815e-05 [partial_unused_args_eliminate]: 2.49001e-06 [add_recomputation]: 0.00020069 [cse_after_recomputation]: 9.461e-05, [1] [Cycle 1]: 8.601e-05, [1] [cse]: 7.619e-05 [environ_conv]: 2.569e-05 [swap_dp_allreduce_reducescatter]: 2.081e-05 [bias_add_comm_swap]: 3.54002e-06 [label_micro_interleaved_index]: 7.26001e-06 [label_fine_grained_interleaved_index]: 2.61e-06 [merge_cast_opt]: 1.60999e-06 [slice_recompute_activation]: 2.31e-06 [micro_interleaved_order_control]: 2.44999e-06 [assign_add_opt]: 1.89e-06 [ForceFp32Comm]: 1.22e-06 [remove_cast_before_assign_add]: 1.72001e-06 [full_micro_interleaved_order_control]: 2.49001e-06 [reorder_send_recv_between_fp_bp]: 3.28e-06 [comm_op_add_attrs]: 1.11002e-06 [add_comm_op_reuse_tag]: 1.15001e-06 [interleave_split_concat_branches]: 1.21002e-06 [interleave_parallel_branches]: 1.09e-06 [overlap_opt_shard_in_pipeline]: 1.60999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.84e-06 [control_data_broadcast_order]: 4.594e-05 [grouped_pairwise_exchange_alltoall]: 1.49e-06 [offloading_packed_experts]: 1.39e-05 [overlap_recompute_and_grad_model_parallel]: 1.389e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.52001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.50001e-06 [overlap_recompute_comm]: 2.53998e-06 [overlap_grad_ring_attention]: 1.1e-05 [overlap_grad_flash_sp]: 0.0139265 [begin_end_overlap_inline]: 2.01e-06 [split_matmul_comm_elemetwise]: 4.75001e-06 [split_layernorm_comm]: 2.04999e-06 [handle_group_info]: 1.47001e-06 [symbol_engine_optimizer]: 0.00093505, [1] [Cycle 1]: 0.00092063, [6] [build]: 0.00034644 [elim_shapecalc]: 6.64e-05 [elim_not_effective]: 7.36e-05 [opt_reshape]: 0.00024021 [fold_const_symbol]: 0.00011053 [renormalize]: 1.13001e-06 [detach_backward]: 5.52999e-06 [pipeline_parallel_scheduler]: 1.81e-06 [auto_monad_reorder]: 7.405e-05 [get_jit_bprop_graph]: 2.36e-06 [rewriter_after_jit_bprop_graph]: 9.49e-06 [opt_after_jit_grad]: 0.140375 [validate]: 0.00014092 Sums bootstrap : 0.000693s : 0.03% type_inference : 1.560026s : 75.85% event_method : 0.000371s : 0.02% auto_monad : 0.001025s : 0.05% graph_reusing : 0.000101s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000281s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000075s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000465s : 0.02% insert-virtual-dataset : 0.000006s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000305s : 0.01% optimize.rewriter_before_opt_a : 0.000979s : 0.05% optimize.opt_a.expand_dump_flag : 0.000045s : 0.00% optimize.opt_a.switch_simplify : 0.001139s : 0.06% optimize.opt_a.loop_unroll : 0.000357s : 0.02% optimize.opt_a.a_1 : 0.165907s : 8.07% optimize.opt_a.with_stream_mark : 0.000253s : 0.01% optimize.opt_a.recompute_prepare : 0.000102s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000052s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000032s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000030s : 0.00% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.002032s : 0.10% optimize.opt_a.accelerated_algorithm : 0.000144s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000067s : 0.00% optimize.opt_a.shard_inline : 0.000067s : 0.00% optimize.opt_a.merge_send_recv : 0.000056s : 0.00% optimize.opt_a.auto_parallel : 0.000049s : 0.00% optimize.opt_a.parallel : 0.000049s : 0.00% optimize.opt_a.flash_sp : 0.000027s : 0.00% optimize.opt_a.merge_comm : 0.000036s : 0.00% optimize.opt_a.allreduce_fusion : 0.000031s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000059s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000077s : 0.00% optimize.opt_a.virtual_dataset : 0.000054s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000055s : 0.00% optimize.opt_a.virtual_output : 0.000074s : 0.00% optimize.opt_a.merge_forward : 0.000042s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000008s : 0.00% optimize.opt_a.offload_activation : 0.000066s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000136s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000105s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000044s : 0.00% optimize.opt_a.meta_fg_expand : 0.000055s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000086s : 0.00% optimize.opt_a.a_after_grad : 0.000086s : 0.00% optimize.opt_a.renormalize : 0.158356s : 7.70% optimize.opt_a.add_forward_monad_depend : 0.000031s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000128s : 0.01% optimize.opt_a.cse : 0.000462s : 0.02% optimize.opt_a.a_3 : 0.000417s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000051s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.001286s : 0.06% optimize.convert_after_rewriter : 0.000051s : 0.00% optimize.order_py_execute_after_rewriter : 0.000016s : 0.00% optimize.mutable_eliminate : 0.001018s : 0.05% optimize.opt_b.b_1 : 0.000693s : 0.03% optimize.opt_b.b_2 : 0.000035s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000032s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000178s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000388s : 0.02% optimize.overlap_param_gather : 0.000005s : 0.00% optimize.cconv : 0.000056s : 0.00% optimize.loop_unroll : 0.000932s : 0.05% optimize.opt_after_cconv.c_1 : 0.000133s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000027s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.cse : 0.000124s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000184s : 0.01% optimize.tuple_transform.d_1 : 0.000277s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000004s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000028s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000201s : 0.01% optimize.cse_after_recomputation.cse : 0.000076s : 0.00% optimize.environ_conv : 0.000026s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000021s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000002s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000046s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000014s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000014s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000011s : 0.00% optimize.overlap_grad_flash_sp : 0.013927s : 0.68% optimize.begin_end_overlap_inline : 0.000002s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000005s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000346s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000066s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000074s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000240s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000111s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000006s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000074s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.140375s : 6.83% validate : 0.000141s : 0.01% Time group info: ------[substitution.] 0.156036 668 0.06% : 0.000086s : 7: substitution.arithmetic_simplify 0.01% : 0.000011s : 7: substitution.depend_value_elim 0.01% : 0.000018s : 17: substitution.elim_not_effective 0.02% : 0.000028s : 20: substitution.float_tuple_getitem_switch 0.04% : 0.000062s : 13: substitution.fold_const_symbol 0.01% : 0.000019s : 20: substitution.graph_param_transform 98.88% : 0.154281s : 100: substitution.inline 0.01% : 0.000018s : 35: substitution.j_node_and_user_rematch 0.03% : 0.000050s : 7: substitution.less_batch_normalization 0.06% : 0.000093s : 3: substitution.list_to_tuple_eliminator_ 0.02% : 0.000035s : 15: substitution.minmaximum_grad 0.05% : 0.000077s : 6: substitution.opt_reshape 0.02% : 0.000025s : 35: substitution.remove_not_recompute_node 0.01% : 0.000012s : 4: substitution.replace_old_param 0.08% : 0.000127s : 29: substitution.reshape_eliminate 0.06% : 0.000095s : 21: substitution.switch_simplify 0.13% : 0.000207s : 60: substitution.tuple_list_convert_item_index_to_positive 0.06% : 0.000095s : 60: substitution.tuple_list_get_item_const_eliminator 0.10% : 0.000158s : 60: substitution.tuple_list_get_item_depend_reorder 0.25% : 0.000389s : 89: substitution.tuple_list_get_item_eliminator 0.10% : 0.000150s : 60: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.559518 2 89.89% : 1.401836s : 1: type_inference.infer 10.11% : 0.157682s : 1: type_inference.specialize ------[replace.] 0.002898 148 3.32% : 0.000096s : 7: replace.depend_value_elim 69.13% : 0.002003s : 100: replace.inline 2.86% : 0.000083s : 3: replace.list_to_tuple_eliminator_ 3.60% : 0.000104s : 3: replace.opt_reshape 14.70% : 0.000426s : 21: replace.switch_simplify 6.39% : 0.000185s : 14: replace.tuple_list_get_item_eliminator ------[match.] 0.154497 148 0.00% : 0.000007s : 7: match.depend_value_elim 99.81% : 0.154196s : 100: match.inline 0.06% : 0.000089s : 3: match.list_to_tuple_eliminator_ 0.05% : 0.000070s : 3: match.opt_reshape 0.05% : 0.000078s : 21: match.switch_simplify 0.04% : 0.000057s : 14: match.tuple_list_get_item_eliminator ------[predicate.] 0.002486 12477 1.04% : 0.000026s : 169: predicate.accumulaten_eliminater 0.78% : 0.000019s : 19: predicate.ad_related_special_op_eliminate 0.44% : 0.000011s : 69: predicate.addn_check_dump 1.06% : 0.000026s : 169: predicate.addn_zero_filter 1.23% : 0.000031s : 169: predicate.adjust_all_reduce_mul_add 2.10% : 0.000052s : 238: predicate.arithmetic_simplify 1.12% : 0.000028s : 169: predicate.cast_eliminate 0.26% : 0.000007s : 40: predicate.check_bprop_eliminate 0.46% : 0.000012s : 69: predicate.compare_switch_simplify 0.07% : 0.000002s : 20: predicate.const_output_eliminate 0.61% : 0.000015s : 73: predicate.depend_value_elim 1.14% : 0.000028s : 169: predicate.dict_get_item_const_eliminator 1.17% : 0.000029s : 169: predicate.dict_get_item_eliminator 1.24% : 0.000031s : 169: predicate.dict_set_item_eliminator 0.42% : 0.000010s : 39: predicate.dumpgradient_eliminate 0.09% : 0.000002s : 20: predicate.elim_not_effective 0.23% : 0.000006s : 20: predicate.elim_shapecalc_of_broadcastargs 1.28% : 0.000032s : 189: predicate.environ_add_const_eliminate 1.11% : 0.000028s : 189: predicate.environ_get_add_eliminate 1.24% : 0.000031s : 189: predicate.environ_get_depend_swap 1.76% : 0.000044s : 258: predicate.environ_get_eliminate 1.46% : 0.000036s : 189: predicate.environ_get_set_eliminate 1.87% : 0.000046s : 286: predicate.exchange_switch_depend_value 2.77% : 0.000069s : 286: predicate.float_depend_g_call 0.47% : 0.000012s : 69: predicate.float_environ_get_switch 0.66% : 0.000016s : 89: predicate.float_tuple_getitem_switch 0.09% : 0.000002s : 19: predicate.fold_const_symbol 0.34% : 0.000009s : 41: predicate.get_grad_eliminate 0.08% : 0.000002s : 20: predicate.graph_param_transform 0.45% : 0.000011s : 69: predicate.incorporate_call 0.42% : 0.000010s : 69: predicate.incorporate_call_switch 6.33% : 0.000157s : 605: predicate.inline 0.39% : 0.000010s : 41: predicate.inline_without_move 0.14% : 0.000003s : 41: predicate.j_node_and_user_rematch 0.43% : 0.000011s : 41: predicate.less_batch_normalization 1.74% : 0.000043s : 226: predicate.list_to_tuple_eliminator_ 2.30% : 0.000057s : 395: predicate.load_eliminater 0.47% : 0.000012s : 20: predicate.loop_unroll_after_grad 3.65% : 0.000091s : 293: predicate.loop_unroll_before_grad 2.42% : 0.000060s : 209: predicate.make_slice_get_slice_eliminator 0.44% : 0.000011s : 69: predicate.merge_addn 0.25% : 0.000006s : 40: predicate.micro_step_allgather_replace 0.26% : 0.000007s : 40: predicate.mini_step_allgather_replace 1.02% : 0.000025s : 169: predicate.minmaximum_grad 0.53% : 0.000013s : 20: predicate.mutable_eliminate 0.24% : 0.000006s : 25: predicate.opt_reshape 0.14% : 0.000003s : 20: predicate.parallel_virtual_node 4.30% : 0.000107s : 286: predicate.partial_defer_inline 1.29% : 0.000032s : 206: predicate.partial_eliminate 0.98% : 0.000024s : 169: predicate.print_const_string_wrapper 0.87% : 0.000022s : 62: predicate.reduce_all_const_elim 1.71% : 0.000042s : 169: predicate.reduce_eliminate 2.52% : 0.000063s : 395: predicate.redundant_stop_gradient_eliminater 0.14% : 0.000004s : 41: predicate.remove_not_recompute_node 0.96% : 0.000024s : 226: predicate.replace_applicator 0.14% : 0.000004s : 41: predicate.replace_old_param 0.08% : 0.000002s : 20: predicate.reset_defer_inline 1.22% : 0.000030s : 169: predicate.reshape_eliminate 0.29% : 0.000007s : 40: predicate.row_tensor_add_zeros_like 0.18% : 0.000004s : 20: predicate.row_tensor_eliminate 0.37% : 0.000009s : 40: predicate.same_eliminate 0.18% : 0.000005s : 48: predicate.set_cell_output_no_recompute 0.34% : 0.000009s : 41: predicate.shard_identity_eliminate 0.29% : 0.000007s : 39: predicate.special_op_eliminate 0.57% : 0.000014s : 69: predicate.specialize_transform 0.37% : 0.000009s : 40: predicate.split_environ_get_set_with_tuple_value 0.31% : 0.000008s : 41: predicate.stack_unstack_eliminate 0.13% : 0.000003s : 20: predicate.switch_call_monad_eliminater 3.39% : 0.000084s : 286: predicate.switch_defer_inline 2.06% : 0.000051s : 326: predicate.switch_layer_defer_inline 7.62% : 0.000190s : 710: predicate.switch_simplify 1.02% : 0.000025s : 169: predicate.tile_eliminate 1.02% : 0.000025s : 169: predicate.transpose_eliminate 1.74% : 0.000043s : 209: predicate.tuple_list_convert_item_index_to_positive 1.77% : 0.000044s : 209: predicate.tuple_list_get_item_const_eliminator 1.67% : 0.000042s : 209: predicate.tuple_list_get_item_depend_reorder 2.92% : 0.000073s : 292: predicate.tuple_list_get_item_eliminator 1.48% : 0.000037s : 209: predicate.tuple_list_get_set_item_eliminator 2.46% : 0.000061s : 278: predicate.tuple_list_set_item_eliminator 1.35% : 0.000034s : 223: predicate.tuple_to_list_eliminator_ 2.16% : 0.000054s : 395: predicate.updatestate_pure_node_eliminater 2.71% : 0.000067s : 464: predicate.updatestate_useless_node_eliminater 0.15% : 0.000004s : 20: predicate.value_based_eliminate 0.32% : 0.000008s : 41: predicate.virtual_dataset_eliminate 0.33% : 0.000008s : 41: predicate.virtual_output_eliminate 0.14% : 0.000003s : 19: predicate.virtual_view_grad_eliminate 0.16% : 0.000004s : 20: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.300162 137 2.69% : 0.008089s : 45: func_graph_cloner_run.FuncGraphClonerGraph 49.91% : 0.149819s : 17: func_graph_cloner_run.FuncGraphClonerNode 47.39% : 0.142254s : 75: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.985968 209 0.00% : 0.000004s : 1: ForceFp32Comm 4.06% : 0.121204s : 1: add_attr 4.06% : 0.121178s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000208s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.04% : 0.001047s : 1: auto_monad 0.00% : 0.000080s : 1: auto_monad_reorder 0.00% : 0.000014s : 1: begin_end_overlap_inline 0.00% : 0.000009s : 1: bias_add_comm_swap 0.03% : 0.000754s : 1: bootstrap 0.00% : 0.000061s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000051s : 1: control_data_broadcast_order 0.00% : 0.000061s : 1: convert_after_rewriter 0.00% : 0.000099s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000010s : 1: detach_backward 0.00% : 0.000029s : 1: environ_conv 0.01% : 0.000394s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000110s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000007s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000012s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000005s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.03% : 0.000950s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.001037s : 1: mutable_eliminate 0.00% : 0.000017s : 1: offloading_packed_experts 0.00% : 0.000063s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000067s : 1: opt.transform.mutable_eliminate 5.71% : 0.170604s : 95: opt.transform.opt_a 0.00% : 0.000131s : 1: opt.transform.opt_after_cconv 0.00% : 0.000147s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000678s : 28: opt.transform.opt_b 0.01% : 0.000300s : 2: opt.transform.opt_trans_graph 0.02% : 0.000477s : 4: opt.transform.symbol_engine_opt 11.11% : 0.331874s : 1: opt_a 0.01% : 0.000372s : 1: opt_after_cconv 4.70% : 0.140412s : 1: opt_after_jit_grad 0.04% : 0.001059s : 1: opt_b 11.88% : 0.354746s : 1: optimize 0.01% : 0.000409s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000020s : 1: order_py_execute_after_rewriter 0.47% : 0.013975s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000014s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000017s : 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% : 0.000006s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.02% : 0.000482s : 1: pre_auto_parallel 0.01% : 0.000321s : 1: py_interpret_to_execute 0.00% : 0.000056s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000193s : 1: remove_dup_value 5.07% : 0.151264s : 1: renormalize.infer 0.24% : 0.007066s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000013s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.001308s : 1: rewriter_after_opt_a 0.03% : 0.001001s : 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% : 0.000009s : 1: split_matmul_comm_elemetwise 0.00% : 0.000025s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000940s : 1: symbol_engine_optimizer 0.01% : 0.000354s : 1: tuple_transform 52.25% : 1.560069s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_v2_dyn_quant_bfloat16[True-True-bfloat16--1-shape3] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant_v2.py::test_swiglu_v2_dyn_quant_bfloat16[True-True-bfloat16--1-shape3],max_mem:116.0M =============================== 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 ================= 16 passed, 25 warnings in 209.63s (0:03:29) ==================