root@davinci-mini:/usr/local/Ascend/mindie/latest/mindie-service# ./bin/mindieservice_daemon
path /configs/mki_cfg.ini does not exist
File size is invalid
ParseIniFileToMapNpLog failed!
ParseLogData failed!
[2025-03-05 05:47:27.64404] [error] [269469] [operation_base.cpp:231] ReshapeAndCacheOperation_2_0_2 CheckIniMatch Failed! Supported Combs:
[comb0]:inTensor0(float16,nd), inTensor1(float16,nd), inTensor2(float16,fractal_nz), inTensor3(float16,fractal_nz), inTensor4(int32,nd),outTensor0(float16,fractal_nz), outTensor1(float16,fractal_nz)
[comb1]:inTensor0(int8,nd), inTensor1(int8,nd), inTensor2(int8,fractal_nz), inTensor3(int8,fractal_nz), inTensor4(int32,nd),outTensor0(int8,fractal_nz), outTensor1(int8,fractal_nz)
[comb2]:inTensor0(bf16,nd), inTensor1(bf16,nd), inTensor2(bf16,fractal_nz), inTensor3(bf16,fractal_nz), inTensor4(int32,nd),outTensor0(bf16,fractal_nz), outTensor1(bf16,fractal_nz)
[2025-03-05 05:47:27.64497] [error] [269469] [operation_base.cpp:267] ReshapeAndCacheOperation_2_0_2 infer shape check fail, error code: 13
[2025-03-05 05:47:27.64508] [error] [269469] [graph_runner.cpp:662] AttentionRunner_2_0:0 node[2] infer shape fail, error code: 13
[2025-03-05 05:47:27.64525] [error] [269469] [graph_runner.cpp:263] AttentionRunner_2_0:0 node[2] setup fail, PreparseNodeVariantPack fail, error code:13
[2025-03-05 05:47:27.64535] [error] [269469] [graph_runner.cpp:762] Prefill_layerRunner_2:0 node[0] setup fail, error code:13
[2025-03-05 05:47:27.64544] [error] [269469] [graph_runner.cpp:270] Prefill_layerRunner_2:0 node[0] SetupNodeRunners fail, error code:13
[2025-03-05 05:47:27.64553] [error] [269469] [operation_base.cpp:462] Prefill_layer_2 runner setup fail
[2025-03-05 05:47:27.64562] [error] [269469] [operation_base.cpp:518] Prefill_layer_2 setup fail, error code: 13
2025-03-05 05:47:27,068 [ERROR] model.py:39 - [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/local/lib/python3.10/dist-packages/model_wrapper/model.py", line 37, in initialize
return self.python_model.initialize(config)
File "/usr/local/lib/python3.10/dist-packages/model_wrapper/standard_model.py", line 144, in initialize
self.generator = Generator(
File "/usr/local/lib/python3.10/dist-packages/mindie_llm/text_generator/generator.py", line 101, in __init__
self.warm_up(max_prefill_tokens, max_seq_len, max_input_len, max_iter_times, inference_mode)
File "/usr/local/lib/python3.10/dist-packages/mindie_llm/text_generator/generator.py", line 245, in warm_up
self.generator_backend.warm_up(model_inputs)
File "/usr/local/lib/python3.10/dist-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 128, in warm_up
_ = self.forward(model_inputs, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/mindie_llm/utils/decorators/time_decorator.py", line 38, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 92, in forward
logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 65, in forward
logits = self.forward_tensor(
File "/usr/local/lib/python3.10/dist-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 92, in forward_tensor
logits = self.model_runner.forward(
File "/root/MindIE-LLM/atb_llm/runner/model_runner.py", line 226, in forward
return self.model.forward(**kwargs)
File "/root/MindIE-LLM/atb_llm/models/base/flash_causal_lm.py", line 469, in forward
logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)
File "/root/MindIE-LLM/atb_llm/models/qwen2/flash_causal_qwen2.py", line 439, in execute_ascend_operator
acl_model_out = model_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.
2025-03-05 05:47:27,072 [ERROR] model.py:42 - [Model] >>> return initialize error result: {'status': 'error', 'npuBlockNum': '0', 'cpuBlockNum': '0'}
2025-03-05 05:47:27.236114 269349 error [llm_infer_model_instance.cpp:45] Initialize modelBackends_ failed.
2025-03-05 05:47:27.236303 269349 error [llm_infer_model.cpp:20] Init model instance failed.
LLMInferEngine failed to init LLMInferModels
ERR: Failed to init endpoint! Please check the service log or console output.
Killed
报错内容如下:
root@davinci-mini:/usr/local/Ascend/mindie/latest/mindie-service# ./bin/mindieservice_daemon path /configs/mki_cfg.ini does not exist File size is invalid ParseIniFileToMapNpLog failed! ParseLogData failed! [2025-03-05 05:47:27.64404] [error] [269469] [operation_base.cpp:231] ReshapeAndCacheOperation_2_0_2 CheckIniMatch Failed! Supported Combs: [comb0]:inTensor0(float16,nd), inTensor1(float16,nd), inTensor2(float16,fractal_nz), inTensor3(float16,fractal_nz), inTensor4(int32,nd),outTensor0(float16,fractal_nz), outTensor1(float16,fractal_nz) [comb1]:inTensor0(int8,nd), inTensor1(int8,nd), inTensor2(int8,fractal_nz), inTensor3(int8,fractal_nz), inTensor4(int32,nd),outTensor0(int8,fractal_nz), outTensor1(int8,fractal_nz) [comb2]:inTensor0(bf16,nd), inTensor1(bf16,nd), inTensor2(bf16,fractal_nz), inTensor3(bf16,fractal_nz), inTensor4(int32,nd),outTensor0(bf16,fractal_nz), outTensor1(bf16,fractal_nz) [2025-03-05 05:47:27.64497] [error] [269469] [operation_base.cpp:267] ReshapeAndCacheOperation_2_0_2 infer shape check fail, error code: 13 [2025-03-05 05:47:27.64508] [error] [269469] [graph_runner.cpp:662] AttentionRunner_2_0:0 node[2] infer shape fail, error code: 13 [2025-03-05 05:47:27.64525] [error] [269469] [graph_runner.cpp:263] AttentionRunner_2_0:0 node[2] setup fail, PreparseNodeVariantPack fail, error code:13 [2025-03-05 05:47:27.64535] [error] [269469] [graph_runner.cpp:762] Prefill_layerRunner_2:0 node[0] setup fail, error code:13 [2025-03-05 05:47:27.64544] [error] [269469] [graph_runner.cpp:270] Prefill_layerRunner_2:0 node[0] SetupNodeRunners fail, error code:13 [2025-03-05 05:47:27.64553] [error] [269469] [operation_base.cpp:462] Prefill_layer_2 runner setup fail [2025-03-05 05:47:27.64562] [error] [269469] [operation_base.cpp:518] Prefill_layer_2 setup fail, error code: 13 2025-03-05 05:47:27,068 [ERROR] model.py:39 - [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/local/lib/python3.10/dist-packages/model_wrapper/model.py", line 37, in initialize return self.python_model.initialize(config) File "/usr/local/lib/python3.10/dist-packages/model_wrapper/standard_model.py", line 144, in initialize self.generator = Generator( File "/usr/local/lib/python3.10/dist-packages/mindie_llm/text_generator/generator.py", line 101, in __init__ self.warm_up(max_prefill_tokens, max_seq_len, max_input_len, max_iter_times, inference_mode) File "/usr/local/lib/python3.10/dist-packages/mindie_llm/text_generator/generator.py", line 245, in warm_up self.generator_backend.warm_up(model_inputs) File "/usr/local/lib/python3.10/dist-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 128, in warm_up _ = self.forward(model_inputs, **kwargs) File "/usr/local/lib/python3.10/dist-packages/mindie_llm/utils/decorators/time_decorator.py", line 38, in wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 92, in forward logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs) File "/usr/local/lib/python3.10/dist-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 65, in forward logits = self.forward_tensor( File "/usr/local/lib/python3.10/dist-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 92, in forward_tensor logits = self.model_runner.forward( File "/root/MindIE-LLM/atb_llm/runner/model_runner.py", line 226, in forward return self.model.forward(**kwargs) File "/root/MindIE-LLM/atb_llm/models/base/flash_causal_lm.py", line 469, in forward logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill) File "/root/MindIE-LLM/atb_llm/models/qwen2/flash_causal_qwen2.py", line 439, in execute_ascend_operator acl_model_out = model_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. 2025-03-05 05:47:27,072 [ERROR] model.py:42 - [Model] >>> return initialize error result: {'status': 'error', 'npuBlockNum': '0', 'cpuBlockNum': '0'} 2025-03-05 05:47:27.236114 269349 error [llm_infer_model_instance.cpp:45] Initialize modelBackends_ failed. 2025-03-05 05:47:27.236303 269349 error [llm_infer_model.cpp:20] Init model instance failed. LLMInferEngine failed to init LLMInferModels ERR: Failed to init endpoint! Please check the service log or console output. Killed