-> llm = LLM(**dataclasses.asdict(engine_args))
(Pdb) n
INFO 07-28 06:48:21 [config.py:841] This model supports multiple tasks: {'classify', 'generate', 'embed', 'reward'}. Defaulting to 'generate'.
INFO 07-28 06:48:21 [config.py:1472] Using max model len 32768
INFO 07-28 06:48:22 [config.py:2285] Chunked prefill is enabled with max_num_batched_tokens=8192.
INFO 07-28 06:48:22 [platform.py:174] PIECEWISE compilation enabled on NPU. use_inductor not supported - using only ACL Graph mode
INFO 07-28 06:48:22 [utils.py:321] Calculated maximum supported batch sizes for ACL graph: 66
INFO 07-28 06:48:22 [utils.py:336] Adjusted ACL graph batch sizes for Qwen2ForCausalLM model (layers: 28): 67 → 66 sizes
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using `tokenizers` before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
INFO 07-28 06:48:23 [core.py:526] Waiting for init message from front-end.
INFO 07-28 06:48:23 [core.py:69] Initializing a V1 LLM engine (v0.9.2) with config: model='/models/z50051264/summary/Qwen2.5-7B', speculative_config=None, tokenizer='/models/z50051264/summary/Qwen2.5-7B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config={}, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=32768, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=True, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=npu, decoding_config=DecodingConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_backend=''), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=0, served_model_name=/models/z50051264/summary/Qwen2.5-7B, num_scheduler_steps=1, multi_step_stream_outputs=True, enable_prefix_caching=True, chunked_prefill_enabled=True, use_async_output_proc=True, pooler_config=None, compilation_config={"level":3,"debug_dump_path":"","cache_dir":"","backend":"","custom_ops":["all"],"splitting_ops":["vllm.unified_attention","vllm.unified_attention_with_output","vllm.unified_ascend_attention_with_output"],"use_inductor":false,"compile_sizes":[],"inductor_compile_config":{},"inductor_passes":{},"use_cudagraph":true,"cudagraph_num_of_warmups":1,"cudagraph_capture_sizes":[512,504,496,488,480,472,464,456,448,440,432,424,416,408,400,392,384,376,368,360,352,344,336,328,320,312,304,296,288,280,272,264,256,240,232,224,216,208,200,192,184,176,168,160,152,144,136,128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],"cudagraph_copy_inputs":false,"full_cuda_graph":false,"max_capture_size":512,"local_cache_dir":null}
ERROR 07-28 06:48:29 [core.py:586] EngineCore failed to start.
ERROR 07-28 06:48:29 [core.py:586] Traceback (most recent call last):
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 577, in run_engine_core
ERROR 07-28 06:48:29 [core.py:586] engine_core = EngineCoreProc(*args, **kwargs)
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 404, in __init__
ERROR 07-28 06:48:29 [core.py:586] super().__init__(vllm_config, executor_class, log_stats,
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 75, in __init__
ERROR 07-28 06:48:29 [core.py:586] self.model_executor = executor_class(vllm_config)
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm/vllm/executor/executor_base.py", line 53, in __init__
ERROR 07-28 06:48:29 [core.py:586] self._init_executor()
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm/vllm/executor/uniproc_executor.py", line 47, in _init_executor
ERROR 07-28 06:48:29 [core.py:586] self.collective_rpc("init_device")
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm/vllm/executor/uniproc_executor.py", line 57, in collective_rpc
ERROR 07-28 06:48:29 [core.py:586] answer = run_method(self.driver_worker, method, args, kwargs)
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm/vllm/utils/__init__.py", line 2736, in run_method
ERROR 07-28 06:48:29 [core.py:586] return func(*args, **kwargs)
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm/vllm/worker/worker_base.py", line 606, in init_device
ERROR 07-28 06:48:29 [core.py:586] self.worker.init_device() # type: ignore
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm-ascend/vllm_ascend/worker/worker_v1.py", line 132, in init_device
ERROR 07-28 06:48:29 [core.py:586] NPUPlatform.set_device(device)
ERROR 07-28 06:48:29 [core.py:586] File "/vllm-workspace/vllm-ascend/vllm_ascend/platform.py", line 98, in set_device
ERROR 07-28 06:48:29 [core.py:586] torch.npu.set_device(device)
ERROR 07-28 06:48:29 [core.py:586] File "/usr/local/python3.10.17/lib/python3.10/site-packages/torch_npu/npu/utils.py", line 80, in set_device
ERROR 07-28 06:48:29 [core.py:586] torch_npu._C._npu_setDevice(device_id)
ERROR 07-28 06:48:29 [core.py:586] RuntimeError: SetPrecisionMode:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:156 NPU function error: at_npu::native::AclSetCompileopt(aclCompileOpt::ACL_PRECISION_MODE, precision_mode), error code is 500001
ERROR 07-28 06:48:29 [core.py:586] [ERROR] 2025-07-28-06:48:29 (PID:3848, Device:0, RankID:-1) ERR00100 PTA call acl api failed
ERROR 07-28 06:48:29 [core.py:586] [Error]: The internal ACL of the system is incorrect.
ERROR 07-28 06:48:29 [core.py:586] Rectify the fault based on the error information in the ascend log.
ERROR 07-28 06:48:29 [core.py:586] E90000: [PID: 3848] 2025-07-28-06:48:29.892.415 Compile operator failed, cause: module '__main__' has no attribute '__spec__' File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/interface.py", line 33, in cann_kb_init
ERROR 07-28 06:48:29 [core.py:586] return RouteServer.initialize(**locals())
ERROR 07-28 06:48:29 [core.py:586] File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 54, in wrapper
ERROR 07-28 06:48:29 [core.py:586] return func(cls, *args, **kwargs)
ERROR 07-28 06:48:29 [core.py:586] File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 169, in initialize
ERROR 07-28 06:48:29 [core.py:586] main_mod, main_path = config_main_info()
ERROR 07-28 06:48:29 [core.py:586] File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/utils/common.py", line 37, in config_main_info
ERROR 07-28 06:48:29 [core.py:586] main_module_name = getattr(main_module.__spec__, "name", None)
ERROR 07-28 06:48:29 [core.py:586]
ERROR 07-28 06:48:29 [core.py:586] TraceBack (most recent call last):
ERROR 07-28 06:48:29 [core.py:586] AOE Failed to call InitCannKB[FUNC:Initialize][FILE:python_adapter_manager.cc][LINE:47]
ERROR 07-28 06:48:29 [core.py:586] Failed to initialize TeConfigInfo.
ERROR 07-28 06:48:29 [core.py:586] [GraphOpt][InitializeInner][InitTbeFunc] Failed to init tbe.[FUNC:InitializeTeFusion][FILE:tbe_op_store_adapter.cc][LINE:1889]
ERROR 07-28 06:48:29 [core.py:586] [GraphOpt][InitializeInner][InitTeFusion]: Failed to initialize TeFusion.[FUNC:InitializeInner][FILE:tbe_op_store_adapter.cc][LINE:1856]
ERROR 07-28 06:48:29 [core.py:586] [SubGraphOpt][PreCompileOp][InitAdapter] InitializeAdapter adapter [tbe_op_adapter] failed! Ret [4294967295][FUNC:InitializeAdapter][FILE:op_store_adapter_manager.cc][LINE:79]
ERROR 07-28 06:48:29 [core.py:586] [SubGraphOpt][PreCompileOp][Init] Initialize op store adapter failed, OpsStoreName[tbe-custom].[FUNC:Initialize][FILE:op_store_adapter_manager.cc][LINE:120]
ERROR 07-28 06:48:29 [core.py:586] [FusionMngr][Init] Op store adapter manager init failed.[FUNC:Initialize][FILE:fusion_manager.cc][LINE:115]
ERROR 07-28 06:48:29 [core.py:586] PluginManager InvokeAll failed.[FUNC:Initialize][FILE:ops_kernel_manager.cc][LINE:83]
ERROR 07-28 06:48:29 [core.py:586] OpsManager initialize failed.[FUNC:InnerInitialize][FILE:gelib.cc][LINE:259]
ERROR 07-28 06:48:29 [core.py:586] GELib::InnerInitialize failed.[FUNC:Initialize][FILE:gelib.cc][LINE:184]
ERROR 07-28 06:48:29 [core.py:586] GEInitialize failed.[FUNC:GEInitialize][FILE:ge_api.cc][LINE:371]
ERROR 07-28 06:48:29 [core.py:586] [Initialize][Ge]GEInitialize failed. ge result = 4294967295[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
ERROR 07-28 06:48:29 [core.py:586] [Init][Compiler]Init compiler failed[FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]
ERROR 07-28 06:48:29 [core.py:586] [Set][Options]OpCompileProcessor init failed![FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]
ERROR 07-28 06:48:29 [core.py:586]
Exception in thread Thread-4:
Process EngineCore_0:
Traceback (most recent call last):
File "/usr/local/python3.10.17/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/utils/multiprocess_util.py", line 91, in run
Traceback (most recent call last):
File "/usr/local/python3.10.17/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/usr/local/python3.10.17/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 590, in run_engine_core
raise e
File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 577, in run_engine_core
engine_core = EngineCoreProc(*args, **kwargs)
File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 404, in __init__
super().__init__(vllm_config, executor_class, log_stats,
key, func, args, kwargs = self.task_q.get(timeout=TIMEOUT)
File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 75, in __init__
self.model_executor = executor_class(vllm_config)
File "<string>", line 2, in get
File "/vllm-workspace/vllm/vllm/executor/executor_base.py", line 53, in __init__
self._init_executor()
File "/vllm-workspace/vllm/vllm/executor/uniproc_executor.py", line 47, in _init_executor
self.collective_rpc("init_device")
File "/vllm-workspace/vllm/vllm/executor/uniproc_executor.py", line 57, in collective_rpc
answer = run_method(self.driver_worker, method, args, kwargs)
File "/vllm-workspace/vllm/vllm/utils/__init__.py", line 2736, in run_method
return func(*args, **kwargs)
File "/vllm-workspace/vllm/vllm/worker/worker_base.py", line 606, in init_device
self.worker.init_device() # type: ignore
File "/vllm-workspace/vllm-ascend/vllm_ascend/worker/worker_v1.py", line 132, in init_device
NPUPlatform.set_device(device)
File "/vllm-workspace/vllm-ascend/vllm_ascend/platform.py", line 98, in set_device
torch.npu.set_device(device)
File "/usr/local/python3.10.17/lib/python3.10/site-packages/torch_npu/npu/utils.py", line 80, in set_device
torch_npu._C._npu_setDevice(device_id)
RuntimeError: SetPrecisionMode:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:156 NPU function error: at_npu::native::AclSetCompileopt(aclCompileOpt::ACL_PRECISION_MODE, precision_mode), error code is 500001
[ERROR] 2025-07-28-06:48:29 (PID:3848, Device:0, RankID:-1) ERR00100 PTA call acl api failed
[Error]: The internal ACL of the system is incorrect.
Rectify the fault based on the error information in the ascend log.
E90000: [PID: 3848] 2025-07-28-06:48:29.892.415 Compile operator failed, cause: module '__main__' has no attribute '__spec__' File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/interface.py", line 33, in cann_kb_init
return RouteServer.initialize(**locals())
File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 54, in wrapper
return func(cls, *args, **kwargs)
File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 169, in initialize
main_mod, main_path = config_main_info()
File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/utils/common.py", line 37, in config_main_info
main_module_name = getattr(main_module.__spec__, "name", None)
TraceBack (most recent call last):
AOE Failed to call InitCannKB[FUNC:Initialize][FILE:python_adapter_manager.cc][LINE:47]
Failed to initialize TeConfigInfo.
[GraphOpt][InitializeInner][InitTbeFunc] Failed to init tbe.[FUNC:InitializeTeFusion][FILE:tbe_op_store_adapter.cc][LINE:1889]
[GraphOpt][InitializeInner][InitTeFusion]: Failed to initialize TeFusion.[FUNC:InitializeInner][FILE:tbe_op_store_adapter.cc][LINE:1856]
[SubGraphOpt][PreCompileOp][InitAdapter] InitializeAdapter adapter [tbe_op_adapter] failed! Ret [4294967295][FUNC:InitializeAdapter][FILE:op_store_adapter_manager.cc][LINE:79]
[SubGraphOpt][PreCompileOp][Init] Initialize op store adapter failed, OpsStoreName[tbe-custom].[FUNC:Initialize][FILE:op_store_adapter_manager.cc][LINE:120]
[FusionMngr][Init] Op store adapter manager init failed.[FUNC:Initialize][FILE:fusion_manager.cc][LINE:115]
PluginManager InvokeAll failed.[FUNC:Initialize][FILE:ops_kernel_manager.cc][LINE:83]
OpsManager initialize failed.[FUNC:InnerInitialize][FILE:gelib.cc][LINE:259]
GELib::InnerInitialize failed.[FUNC:Initialize][FILE:gelib.cc][LINE:184]
GEInitialize failed.[FUNC:GEInitialize][FILE:ge_api.cc][LINE:371]
[Initialize][Ge]GEInitialize failed. ge result = 4294967295[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
[Init][Compiler]Init compiler failed[FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]
[Set][Options]OpCompileProcessor init failed![FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]
RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {'EngineCore_0': 1}
> /models/z50051264/vllm-0.10.0/benchmarks/benchmark_throughput.py(62)run_vllm()
-> llm = LLM(**dataclasses.asdict(engine_args))
初始化引擎失败是怎么回事儿？？？
最新发布
本文介绍如何在IntelliJ IDEA中正确配置@Override注解，确保在使用Java接口实现类时不会出现错误提示。需要设置项目的语言级别为1.6及以上，并调整模块设置。
扫一扫
1590
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
