【长沙AICC】910A环境，Qwen3-30B-A3B模型基于MindIE运行推理任务，Gating算子不支持

910A 环境，基于MindIE T18镜像推理 Qwen3-30B-A3B模型缺少Gating算子，官方是否有计划对该算子进行支持。如果社区贡献自行实现，昇腾是否有完善的patch 算子架构支持？

```
[2025-06-19 18:28:56.563037] [error] [71373] [operation_base.cpp:76] Kernel GatingKernel is not found, maybe it's not supported in this soc
[2025-06-19 18:28:56.563105] [error] [71373] [mki_node_implement.cpp:91] GatingOpsRunner_3_3_5_0_0[0] GatingOperation get best kernel fail, kernel count:0
[2025-06-19 18:28:56.563117] [error] [71373] [ops_runner.cpp:678] GatingOpsRunner_3_3_5_0_0:0  node[0] GatingOperation update best kernel failed
[2025-06-19 18:28:56.563132] [error] [71373] [ops_runner.cpp:713] GatingOpsRunner_3_3_5_0_0:0  node[0] get best node's kernel fail
[2025-06-19 18:28:56.563142] [error] [71373] [ops_runner.cpp:659] GatingOpsRunner_3_3_5_0_0:0  node[0] plan kernel graph fail
[2025-06-19 18:28:56.563150] [error] [71373] [ops_runner.cpp:212] GatingOpsRunner_3_3_5_0_0:0 PlanKernelGraph fail
[2025-06-19 18:28:56.563157] [error] [71373] [graph_runner.cpp:786] MoeMlpRunner_3_3_5_0:0  node[0] setup fail, error code:1
[2025-06-19 18:28:56.563164] [error] [71373] [graph_runner.cpp:293] MoeMlpRunner_3_3_5_0:0 node[0] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.563172] [error] [71373] [graph_runner.cpp:786] DynamicEpMoERunner_3_3_5:0  node[0] setup fail, error code:1
[2025-06-19 18:28:56.563182] [error] [71373] [graph_runner.cpp:293] DynamicEpMoERunner_3_3_5:0 node[0] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.563189] [error] [71373] [graph_runner.cpp:786] SparseMoeRunner_3_3:0  node[5] setup fail, error code:1
[2025-06-19 18:28:56.563195] [error] [71373] [graph_runner.cpp:293] SparseMoeRunner_3_3:0 node[5] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.563201] [error] [71373] [graph_runner.cpp:786] Prefill_layerRunner_3:0  node[3] setup fail, error code:1
[2025-06-19 18:28:56.563207] [error] [71373] [graph_runner.cpp:293] Prefill_layerRunner_3:0 node[3] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.563212] [error] [71373] [operation_base.cpp:462] Prefill_layer_3 runner setup fail
[2025-06-19 18:28:56.563218] [error] [71373] [operation_base.cpp:519] Prefill_layer_3 setup fail, error code: 1
[2025-06-19 18:28:56.563519] [error] [71358] [operation_base.cpp:76] Kernel GatingKernel is not found, maybe it's not supported in this soc
[2025-06-19 18:28:56.563585] [error] [71358] [mki_node_implement.cpp:91] GatingOpsRunner_3_3_5_0_0[0] GatingOperation get best kernel fail, kernel count:0
[2025-06-19 18:28:56.563596] [error] [71358] [ops_runner.cpp:678] GatingOpsRunner_3_3_5_0_0:0  node[0] GatingOperation update best kernel failed
[2025-06-19 18:28:56.563612] [error] [71358] [ops_runner.cpp:713] GatingOpsRunner_3_3_5_0_0:0  node[0] get best node's kernel fail
[2025-06-19 18:28:56.563625] [error] [71358] [ops_runner.cpp:659] GatingOpsRunner_3_3_5_0_0:0  node[0] plan kernel graph fail
[2025-06-19 18:28:56.563633] [error] [71358] [ops_runner.cpp:212] GatingOpsRunner_3_3_5_0_0:0 PlanKernelGraph fail
[2025-06-19 18:28:56.563641] [error] [71358] [graph_runner.cpp:786] MoeMlpRunner_3_3_5_0:0  node[0] setup fail, error code:1
[2025-06-19 18:28:56.563648] [error] [71358] [graph_runner.cpp:293] MoeMlpRunner_3_3_5_0:0 node[0] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.563655] [error] [71358] [graph_runner.cpp:786] DynamicEpMoERunner_3_3_5:0  node[0] setup fail, error code:1
[2025-06-19 18:28:56.563664] [error] [71358] [graph_runner.cpp:293] DynamicEpMoERunner_3_3_5:0 node[0] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.563672] [error] [71358] [graph_runner.cpp:786] SparseMoeRunner_3_3:0  node[5] setup fail, error code:1
[2025-06-19 18:28:56.563681] [error] [71358] [graph_runner.cpp:293] SparseMoeRunner_3_3:0 node[5] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.563690] [error] [71358] [graph_runner.cpp:786] Prefill_layerRunner_3:0  node[3] setup fail, error code:1
[2025-06-19 18:28:56.563698] [error] [71358] [graph_runner.cpp:293] Prefill_layerRunner_3:0 node[3] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.563708] [error] [71358] [operation_base.cpp:462] Prefill_layer_3 runner setup fail
[2025-06-19 18:28:56.563716] [error] [71358] [operation_base.cpp:519] Prefill_layer_3 setup fail, error code: 1
[2025-06-19 18:28:56.564349] [error] [71359] [operation_base.cpp:76] Kernel GatingKernel is not found, maybe it's not supported in this soc
[2025-06-19 18:28:56.564420] [error] [71359] [mki_node_implement.cpp:91] GatingOpsRunner_3_3_5_0_0[0] GatingOperation get best kernel fail, kernel count:0
[2025-06-19 18:28:56.564433] [error] [71359] [ops_runner.cpp:678] GatingOpsRunner_3_3_5_0_0:0  node[0] GatingOperation update best kernel failed
[2025-06-19 18:28:56.564447] [error] [71359] [ops_runner.cpp:713] GatingOpsRunner_3_3_5_0_0:0  node[0] get best node's kernel fail
[2025-06-19 18:28:56.564460] [error] [71359] [ops_runner.cpp:659] GatingOpsRunner_3_3_5_0_0:0  node[0] plan kernel graph fail
[2025-06-19 18:28:56.564468] [error] [71359] [ops_runner.cpp:212] GatingOpsRunner_3_3_5_0_0:0 PlanKernelGraph fail
[2025-06-19 18:28:56.564479] [error] [71359] [graph_runner.cpp:786] MoeMlpRunner_3_3_5_0:0  node[0] setup fail, error code:1
[2025-06-19 18:28:56.564487] [error] [71359] [graph_runner.cpp:293] MoeMlpRunner_3_3_5_0:0 node[0] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.564495] [error] [71359] [graph_runner.cpp:786] DynamicEpMoERunner_3_3_5:0  node[0] setup fail, error code:1
[2025-06-19 18:28:56.564502] [error] [71359] [graph_runner.cpp:293] DynamicEpMoERunner_3_3_5:0 node[0] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.564510] [error] [71359] [graph_runner.cpp:786] SparseMoeRunner_3_3:0  node[5] setup fail, error code:1
[2025-06-19 18:28:56.564517] [error] [71359] [graph_runner.cpp:293] SparseMoeRunner_3_3:0 node[5] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.564525] [error] [71359] [graph_runner.cpp:786] Prefill_layerRunner_3:0  node[3] setup fail, error code:1
[2025-06-19 18:28:56.564532] [error] [71359] [graph_runner.cpp:293] Prefill_layerRunner_3:0 node[3] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.564540] [error] [71359] [operation_base.cpp:462] Prefill_layer_3 runner setup fail
[2025-06-19 18:28:56.564549] [error] [71359] [operation_base.cpp:519] Prefill_layer_3 setup fail, error code: 1
[2025-06-19 18:28:56.564966] [error] [71374] [operation_base.cpp:76] Kernel GatingKernel is not found, maybe it's not supported in this soc
[2025-06-19 18:28:56.565023] [error] [71374] [mki_node_implement.cpp:91] GatingOpsRunner_3_3_5_0_0[0] GatingOperation get best kernel fail, kernel count:0
[2025-06-19 18:28:56.565035] [error] [71374] [ops_runner.cpp:678] GatingOpsRunner_3_3_5_0_0:0  node[0] GatingOperation update best kernel failed
[2025-06-19 18:28:56.565050] [error] [71374] [ops_runner.cpp:713] GatingOpsRunner_3_3_5_0_0:0  node[0] get best node's kernel fail
[2025-06-19 18:28:56.565059] [error] [71374] [ops_runner.cpp:659] GatingOpsRunner_3_3_5_0_0:0  node[0] plan kernel graph fail
[2025-06-19 18:28:56.565067] [error] [71374] [ops_runner.cpp:212] GatingOpsRunner_3_3_5_0_0:0 PlanKernelGraph fail
[2025-06-19 18:28:56.565075] [error] [71374] [graph_runner.cpp:786] MoeMlpRunner_3_3_5_0:0  node[0] setup fail, error code:1
[2025-06-19 18:28:56.565084] [error] [71374] [graph_runner.cpp:293] MoeMlpRunner_3_3_5_0:0 node[0] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.565092] [error] [71374] [graph_runner.cpp:786] DynamicEpMoERunner_3_3_5:0  node[0] setup fail, error code:1
[2025-06-19 18:28:56.565099] [error] [71374] [graph_runner.cpp:293] DynamicEpMoERunner_3_3_5:0 node[0] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.565107] [error] [71374] [graph_runner.cpp:786] SparseMoeRunner_3_3:0  node[5] setup fail, error code:1
[2025-06-19 18:28:56.565115] [error] [71374] [graph_runner.cpp:293] SparseMoeRunner_3_3:0 node[5] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.565122] [error] [71374] [graph_runner.cpp:786] Prefill_layerRunner_3:0  node[3] setup fail, error code:1
[2025-06-19 18:28:56.565129] [error] [71374] [graph_runner.cpp:293] Prefill_layerRunner_3:0 node[3] SetupNodeRunners fail, error code:1
[2025-06-19 18:28:56.565137] [error] [71374] [operation_base.cpp:462] Prefill_layer_3 runner setup fail
[2025-06-19 18:28:56.565144] [error] [71374] [operation_base.cpp:519] Prefill_layer_3 setup fail, error code: 1
[2025-06-19 18:28:56.019+0800] [70446] [281473646981344] [batchscheduler] [ERROR] [model.py:59] : [Model]	>>> Exception:Setup fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document.
Traceback (most recent call last):
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/model_wrapper/model.py", line 57, in initialize
    return self.python_model.initialize(config)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 117, in initialize
    self.generator = Generator(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 229, in __init__
    self.cache_manager = self.warm_up(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 426, in warm_up
    raise e
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 419, in warm_up
    self._generate_inputs_warm_up_backend(cache_manager, input_metadata, inference_mode, dummy=True)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 522, in _generate_inputs_warm_up_backend
    self.generator_backend._warm_up(model_inputs, inference_mode=inference_mode)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 519, in _warm_up
    super()._warm_up(model_inputs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 219, in _warm_up
    _ = self.forward(model_inputs, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/utils/decorators/time_decorator.py", line 69, in wrapper
    return func(*args, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 209, in forward
    logits = self._forward(model_inputs, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 539, in _forward
    logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 164, in forward
    result = self.forward_tensor(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 204, in forward_tensor
    result = self.model_runner.forward(
  File "/usr/local/Ascend/atb-models/atb_llm/runner/model_runner.py", line 297, in forward
    res = self.model.forward(**kwargs)
  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 501, in forward
    logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)
  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 434, in execute_ascend_operator
    acl_model_out = self.acl_encoder_operation.execute(acl_inputs, acl_param)
RuntimeError: Setup fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document.

[2025-06-19 18:28:56.019+0800] [70446] [281473646981344] [batchscheduler] [ERROR] [model.py:62] : [MIE04E13030A] [Model]	>>> return initialize error result: {'status': 'error', 'npuBlockNum': '0', 'cpuBlockNum': '0', 'memPoolId': '-1'}
[2025-06-19 18:28:56.019+0800] [70455] [281473181413600] [batchscheduler] [ERROR] [model.py:59] : [Model]	>>> Exception:Setup fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document.
Traceback (most recent call last):
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/model_wrapper/model.py", line 57, in initialize
    return self.python_model.initialize(config)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 117, in initialize
    self.generator = Generator(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 229, in __init__
    self.cache_manager = self.warm_up(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 426, in warm_up
    raise e
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 419, in warm_up
    self._generate_inputs_warm_up_backend(cache_manager, input_metadata, inference_mode, dummy=True)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 522, in _generate_inputs_warm_up_backend
    self.generator_backend._warm_up(model_inputs, inference_mode=inference_mode)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 519, in _warm_up
    super()._warm_up(model_inputs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 219, in _warm_up
    _ = self.forward(model_inputs, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/utils/decorators/time_decorator.py", line 69, in wrapper
    return func(*args, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 209, in forward
    logits = self._forward(model_inputs, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 539, in _forward
    logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 164, in forward
    result = self.forward_tensor(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 204, in forward_tensor
    result = self.model_runner.forward(
  File "/usr/local/Ascend/atb-models/atb_llm/runner/model_runner.py", line 297, in forward
    res = self.model.forward(**kwargs)
  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 501, in forward
    logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)
  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 434, in execute_ascend_operator
    acl_model_out = self.acl_encoder_operation.execute(acl_inputs, acl_param)
RuntimeError: Setup fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document.

[2025-06-19 18:28:56.019+0800] [70455] [281473181413600] [batchscheduler] [ERROR] [model.py:62] : [MIE04E13030A] [Model]	>>> return initialize error result: {'status': 'error', 'npuBlockNum': '0', 'cpuBlockNum': '0', 'memPoolId': '-1'}
[2025-06-19 18:28:56.019+0800] [70442] [281473516957920] [batchscheduler] [ERROR] [model.py:59] : [Model]	>>> Exception:Setup fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document.
Traceback (most recent call last):
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/model_wrapper/model.py", line 57, in initialize
    return self.python_model.initialize(config)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 117, in initialize
    self.generator = Generator(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 229, in __init__
    self.cache_manager = self.warm_up(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 426, in warm_up
    raise e
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 419, in warm_up
    self._generate_inputs_warm_up_backend(cache_manager, input_metadata, inference_mode, dummy=True)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 522, in _generate_inputs_warm_up_backend
    self.generator_backend._warm_up(model_inputs, inference_mode=inference_mode)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 519, in _warm_up
    super()._warm_up(model_inputs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 219, in _warm_up
    _ = self.forward(model_inputs, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/utils/decorators/time_decorator.py", line 69, in wrapper
    return func(*args, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 209, in forward
    logits = self._forward(model_inputs, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 539, in _forward
    logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 164, in forward
    result = self.forward_tensor(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 204, in forward_tensor
    result = self.model_runner.forward(
  File "/usr/local/Ascend/atb-models/atb_llm/runner/model_runner.py", line 297, in forward
    res = self.model.forward(**kwargs)
  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 501, in forward
    logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)
  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 434, in execute_ascend_operator
    acl_model_out = self.acl_encoder_operation.execute(acl_inputs, acl_param)
RuntimeError: Setup fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document.

[2025-06-19 18:28:56.019+0800] [70442] [281473516957920] [batchscheduler] [ERROR] [model.py:62] : [MIE04E13030A] [Model]	>>> return initialize error result: {'status': 'error', 'npuBlockNum': '0', 'cpuBlockNum': '0', 'memPoolId': '-1'}
[2025-06-19 18:28:56.019+0800] [70444] [281472845869280] [batchscheduler] [ERROR] [model.py:59] : [Model]	>>> Exception:Setup fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document.
Traceback (most recent call last):
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/model_wrapper/model.py", line 57, in initialize
    return self.python_model.initialize(config)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 117, in initialize
    self.generator = Generator(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 229, in __init__
    self.cache_manager = self.warm_up(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 426, in warm_up
    raise e
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 419, in warm_up
    self._generate_inputs_warm_up_backend(cache_manager, input_metadata, inference_mode, dummy=True)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 522, in _generate_inputs_warm_up_backend
    self.generator_backend._warm_up(model_inputs, inference_mode=inference_mode)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 519, in _warm_up
    super()._warm_up(model_inputs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 219, in _warm_up
    _ = self.forward(model_inputs, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/utils/decorators/time_decorator.py", line 69, in wrapper
    return func(*args, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 209, in forward
    logits = self._forward(model_inputs, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 539, in _forward
    logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 164, in forward
    result = self.forward_tensor(
  File "/usr/lib/Python3.10.0/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 204, in forward_tensor
    result = self.model_runner.forward(
  File "/usr/local/Ascend/atb-models/atb_llm/runner/model_runner.py", line 297, in forward
    res = self.model.forward(**kwargs)
  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 501, in forward
    logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)
  File "/usr/local/Ascend/atb-models/atb_llm/models/base/flash_causal_lm.py", line 434, in execute_ascend_operator
    acl_model_out = self.acl_encoder_operation.execute(acl_inputs, acl_param)
RuntimeError: Setup fail, enable log: export ASDOPS_LOG_LEVEL=ERROR, export ASDOPS_LOG_TO_STDOUT=1 to find the first error. For more details, see the MindIE official document.

[2025-06-19 18:28:56.019+0800] [70444] [281472845869280] [batchscheduler] [ERROR] [model.py:62] : [MIE04E13030A] [Model]	>>> return initialize error result: {'status': 'error', 'npuBlockNum': '0', 'cpuBlockNum': '0', 'memPoolId': '-1'}
[2025-06-19 18:28:56.811+08:00] [70160] [70162] [server] [WARN] [llm_daemon.cpp:74] : [MIE04W01011A] [daemon] Received exit signal[17]
[2025-06-19 18:28:56.811+08:00] [70160] [70162] [server] [ERROR] [llm_daemon.cpp:90] : [MIE04E010109] [daemon] Process 70446 was terminated by signal 9 (Killed)
[2025-06-19 18:28:56.849+08:00] [70160] [70160] [server] [WARN] [llm_daemon.cpp:74] : [MIE04W01011A] [daemon] Received exit signal[17]
[2025-06-19 18:28:56.849+08:00] [70160] [70160] [server] [ERROR] [llm_daemon.cpp:90] : [MIE04E010109] [daemon] Process 70455 was terminated by signal 9 (Killed)
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
[ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared!
/usr/lib/Python3.10.0/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 30 leaked semaphore objects to clean up at shutdown
  warnings.warn('resource_tracker: There appear to be %d '
/usr/lib/Python3.10.0/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 30 leaked semaphore objects to clean up at shutdown
  warnings.warn('resource_tracker: There appear to be %d '
/usr/lib/Python3.10.0/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 30 leaked semaphore objects to clean up at shutdown
  warnings.warn('resource_tracker: There appear to be %d '
/usr/lib/Python3.10.0/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 30 leaked semaphore objects to clean up at shutdown
  warnings.warn('resource_tracker: There appear to be %d '

Daemon is killing...
Killed

```

Ascend/ModelZoo-PyTorch

内容风险标识

评论 (0)

Ascend/ModelZoo-PyTorch .gitee-modal { width: 500px !important; }

内容风险标识