ERROR 07-25 15:40:31 [core.py:586] EngineCore failed to start.
ERROR 07-25 15:40:31 [core.py:586] Traceback (most recent call last):
ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 577, in run_engine_core
ERROR 07-25 15:40:31 [core.py:586] engine_core = EngineCoreProc(*args, **kwargs)
ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 404, in __init__
ERROR 07-25 15:40:31 [core.py:586] super().__init__(vllm_config, executor_class, log_stats,
ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 75, in __init__
ERROR 07-25 15:40:31 [core.py:586] self.model_executor = executor_class(vllm_config)
ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/executor/executor_base.py", line 53, in __init__
ERROR 07-25 15:40:31 [core.py:586] self._init_executor()
ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/executor/multiproc_executor.py", line 93, in _init_executor
ERROR 07-25 15:40:31 [core.py:586] self.workers = WorkerProc.wait_for_ready(unready_workers)
ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/executor/multiproc_executor.py", line 422, in wait_for_ready
ERROR 07-25 15:40:31 [core.py:586] raise e from None
ERROR 07-25 15:40:31 [core.py:586] Exception: WorkerProc initialization failed due to an exception in a background process. See stack trace for root cause.
Process EngineCore_0:
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,
File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 75, in __init__
self.model_executor = executor_class(vllm_config)
File "/vllm-workspace/vllm/vllm/executor/executor_base.py", line 53, in __init__
self._init_executor()
File "/vllm-workspace/vllm/vllm/v1/executor/multiproc_executor.py", line 93, in _init_executor
self.workers = WorkerProc.wait_for_ready(unready_workers)
File "/vllm-workspace/vllm/vllm/v1/executor/multiproc_executor.py", line 422, in wait_for_ready
raise e from None
Exception: WorkerProc initialization failed due to an exception in a background process. See stack trace for root cause.
Traceback (most recent call last):
File "/workspace/test/vllm_demo.py", line 42, in <module>
main()
File "/workspace/test/vllm_demo.py", line 19, in main
llm = LLM(
File "/vllm-workspace/vllm/vllm/entrypoints/llm.py", line 271, in __init__
self.llm_engine = LLMEngine.from_engine_args(
File "/vllm-workspace/vllm/vllm/engine/llm_engine.py", line 501, in from_engine_args
return engine_cls.from_vllm_config(
File "/vllm-workspace/vllm/vllm/v1/engine/llm_engine.py", line 124, in from_vllm_config
return cls(vllm_config=vllm_config,
File "/vllm-workspace/vllm/vllm/v1/engine/llm_engine.py", line 101, in __init__
self.engine_core = EngineCoreClient.make_client(
File "/vllm-workspace/vllm/vllm/v1/engine/core_client.py", line 75, in make_client
return SyncMPClient(vllm_config, executor_class, log_stats)
File "/vllm-workspace/vllm/vllm/v1/engine/core_client.py", line 503, in __init__
super().__init__(
File "/vllm-workspace/vllm/vllm/v1/engine/core_client.py", line 403, in __init__
with launch_core_engines(vllm_config, executor_class,
File "/usr/local/python3.10.17/lib/python3.10/contextlib.py", line 142, in __exit__
next(self.gen)
File "/vllm-workspace/vllm/vllm/v1/engine/utils.py", line 434, in launch_core_engines
/usr/local/python3.10.17/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 2 leaked shared_memory objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
wait_for_engine_startup(
File "/vllm-workspace/vllm/vllm/v1/engine/utils.py", line 484, in wait_for_engine_startup
raise RuntimeError("Engine core initialization failed. "
RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {'EngineCore_0': 1}
[ERROR] 2025-07-25-15:40:31 (PID:37468, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception
我在 Ascend 910B 上使用 vLLM 0.9.2rc1 运行 DeepSeek-R1-bf16-hfd-w8a8 模型时遇到问题,服务无法启动,报错如下:
RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {'EngineCore_0': 1}
环境如下
Collecting environment information... INFO 07-25 15:38:53 [__init__.py:39] Available plugins for group vllm.platform_plugins: INFO 07-25 15:38:53 [__init__.py:41] - ascend -> vllm_ascend:register INFO 07-25 15:38:53 [__init__.py:44] All plugins in this group will be loaded. Set `VLLM_PLUGINS` to control which plugins to load. INFO 07-25 15:38:53 [__init__.py:235] Platform plugin ascend is activated WARNING 07-25 15:38:53 [_custom_ops.py:20] Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm._C'") ================================================================================ DeepSeek-Ascend Environment Report ================================================================================ System Info: ----------- OS: Linux-5.4.0-153-generic-x86_64-with-glibc2.35 Hostname: infra-gpu-npu-062.host.shzhisuan.com Python Version: 3.10.17 (main, May 8 2025, 07:16:11) [GCC 11.4.0] Python Platform: Linux-5.4.0-153-generic-x86_64-with-glibc2.35 CPU Info: Intel(R) Xeon(R) Platinum 8468 CPU Cores: 192 System Time: 2025-07-25 15:38:50 Python Packages: --------------- Installed Packages: - te==0.4.0 - auto-tune==0.1.0 - hccl==0.1.0 - hccl-parser==0.1 - msobjdump==0.1.0 - op-compile-tool==0.1.0 - op-gen==0.1 - op-test-frame==0.1 - opc-tool==0.1.0 - show-kernel-debug-data==0.1.0 - dataflow==0.0.1 - llm-datadist==0.0.1 - schedule-search==0.0.1 - airportsdata==20250706 - fsspec==2025.5.1 - certifi==2025.4.26 - jsonschema-specifications==2025.4.1 - regex==2024.11.6 - setuptools==65.5.0 - pyzmq==27.0.0 - attrs==25.3.0 - pip==25.1.1 - packaging==25.0 - pycountry==24.6.1 - aiofiles==24.1.0 - websockets==15.0.1 - rich==14.0.0 - pillow==11.3.0 - py-cpuinfo==9.0.0 - setuptools-scm==8.3.1 - click==8.2.1 - prometheus-fastapi-instrumentator==7.1.0 - psutil==7.0.0 - multidict==6.6.3 - hyperframe==6.1.0 - cachetools==6.1.0 - pyyaml==6.0.2 - diskcache==5.6.3 - decorator==5.2.1 - async-timeout==5.0.1 - tqdm==4.67.1 - transformers==4.52.4 - jsonschema==4.24.0 - typing-extensions==4.14.1 - opencv-python-headless==4.12.0.88 - anyio==4.9.0 - h2==4.2.0 - hpack==4.1.0 - cmake==4.0.3 - protobuf==3.20.0 - filelock==3.18.0 - aiohttp==3.12.14 - idna==3.10 - charset-normalizer==3.4.2 - networkx==3.4.2 - python-json-logger==3.3.0 - jinja2==3.1.6 - werkzeug==3.1.3 - flask==3.1.1 - cloudpickle==3.1.1 - cython==3.0.12 - markupsafe==3.0.2 - pybind11==3.0.0 - markdown-it-py==3.0.0 - ray==2.47.1 - pydantic-core==2.33.2 - requests==2.32.3 - sentry-sdk==2.32.0 - pycparser==2.22 - pygments==2.19.2 - pydantic==2.11.7 - dnspython==2.7.0 - aiohappyeyeballs==2.6.1 - torch-npu==2.5.1.post1.dev20250619 - torch==2.5.1+cpu - urllib3==2.4.0 - pathlib2==2.3.7.post1 - absl-py==2.2.2 - tomli==2.2.1 - itsdangerous==2.2.0 - email-validator==2.2.0 - priority==2.0.0 - openai==1.90.0 - modelscope==1.28.0 - numpy==1.26.4 - yarl==1.20.1 - cffi==1.17.1 - six==1.17.0 - scipy==1.15.2 - sympy==1.13.1 - ninja==1.11.1.4 - blinker==1.9.0 - distro==1.9.0 - frozenlist==1.7.0 - mistral-common==1.7.0 - nest-asyncio==1.6.0 - shellingham==1.5.4 - pybase64==1.4.1 - aiosignal==1.4.0 - sniffio==1.3.1 - mpmath==1.3.0 - exceptiongroup==1.3.0 - lark==1.2.2 - wsproto==1.2.0 - hf-xet==1.1.5 - msgpack==1.1.1 - python-dotenv==1.1.1 - watchfiles==1.1.0 - httpcore==1.0.9 - blake3==1.0.5 - fastapi==0.116.0 - numba==0.61.2 - starlette==0.46.2 - wheel==0.45.1 - llvmlite==0.44.0 - referencing==0.36.2 - uvicorn==0.35.0 - huggingface-hub==0.33.3 - httpx==0.28.1 - rpds-py==0.26.0 - prometheus-client==0.22.1 - tokenizers==0.21.2 - uvloop==0.21.0 - torchvision==0.20.1+cpu - quart==0.20.0 - msgspec==0.19.0 - depyf==0.18.0 - hypercorn==0.17.3 - gguf==0.17.1 - h11==0.16.0 - typer==0.16.0 - rich-toolkit==0.14.8 - lm-format-enforcer==0.10.11 - compressed-tensors==0.10.2 - jiter==0.10.0 - vllm==0.9.2+empty - vllm-ascend==0.9.2rc1 - tiktoken==0.9.0 - astor==0.8.1 - einops==0.8.1 - llguidance==0.7.30 - annotated-types==0.7.0 - httptools==0.6.4 - safetensors==0.5.3 - rignore==0.5.1 - typing-inspection==0.4.1 - dill==0.4.0 - interegular==0.3.3 - propcache==0.3.2 - taskgroup==0.2.2 - partial-json-parser==0.2.1.1.post6 - sentencepiece==0.2.0 - outlines-core==0.1.26 - xgrammar==0.1.19 - outlines==0.1.11 - fastapi-cloud-cli==0.1.2 - mdurl==0.1.2 - python-multipart==0.0.20 - fastapi-cli==0.0.8 Pip Version: pip 25.1.1 from /usr/local/python3.10.17/lib/python3.10/site-packages/pip (python 3.10) Conda Version: Not using conda PyTorch Info: ------------ PyTorch Version: 2.5.1+cpu PyTorch NPU Available: True PyTorch NPU Device Count: 16 PyTorch NPU Device Name: Ascend910B2C PyTorch CUDA Available: False PyTorch Backend: False NPU Info: -------- NPU-SMI Output: +------------------------------------------------------------------------------------------------+ | npu-smi 24.1.rc3 Version: 24.1.rc3 | +---------------------------+---------------+----------------------------------------------------+ | NPU Name | Health | Power(W) Temp(C) Hugepages-Usage(page)| | Chip | Bus-Id | AICore(%) Memory-Usage(MB) HBM-Usage(MB) | +===========================+===============+====================================================+ | 0 910B2C | OK | 92.1 45 0 / 0 | | 0 | 0000:5A:00.0 | 0 0 / 0 3383 / 65536 | +===========================+===============+====================================================+ | 1 910B2C | OK | 95.6 44 0 / 0 | | 0 | 0000:19:00.0 | 0 0 / 0 3384 / 65536 | +===========================+===============+====================================================+ | 2 910B2C | OK | 91.9 44 0 / 0 | | 0 | 0000:49:00.0 | 0 0 / 0 3381 / 65536 | +===========================+===============+====================================================+ | 3 910B2C | OK | 91.9 45 0 / 0 | | 0 | 0000:39:00.0 | 0 0 / 0 3381 / 65536 | +===========================+===============+====================================================+ | 4 910B2C | OK | 100.1 43 0 / 0 | | 0 | 0000:DA:00.0 | 0 0 / 0 3380 / 65536 | +===========================+===============+====================================================+ | 5 910B2C | OK | 96.5 44 0 / 0 | | 0 | 0000:99:00.0 | 0 0 / 0 3381 / 65536 | +===========================+===============+====================================================+ | 6 910B2C | OK | 93.7 44 0 / 0 | | 0 | 0000:B8:00.0 | 0 0 / 0 3380 / 65536 | +===========================+===============+====================================================+ | 7 910B2C | OK | 91.8 43 0 / 0 | | 0 | 0000:C8:00.0 | 0 0 / 0 3382 / 65536 | +===========================+===============+====================================================+ | 8 910B2C | OK | 89.1 43 0 / 0 | | 0 | 0000:59:00.0 | 0 0 / 0 3378 / 65536 | +===========================+===============+====================================================+ | 9 910B2C | OK | 94.9 44 0 / 0 | | 0 | 0000:18:00.0 | 0 0 / 0 3381 / 65536 | +===========================+===============+====================================================+ | 10 910B2C | OK | 91.6 43 0 / 0 | | 0 | 0000:48:00.0 | 0 0 / 0 3382 / 65536 | +===========================+===============+====================================================+ | 11 910B2C | OK | 97.3 45 0 / 0 | | 0 | 0000:38:00.0 | 0 0 / 0 3382 / 65536 | +===========================+===============+====================================================+ | 12 910B2C | OK | 92.2 43 0 / 0 | | 0 | 0000:D9:00.0 | 0 0 / 0 3382 / 65536 | +===========================+===============+====================================================+ | 13 910B2C | OK | 94.7 43 0 / 0 | | 0 | 0000:98:00.0 | 0 0 / 0 3382 / 65536 | +===========================+===============+====================================================+ | 14 910B2C | OK | 92.4 42 0 / 0 | | 0 | 0000:B9:00.0 | 0 0 / 0 3379 / 65536 | +===========================+===============+====================================================+ | 15 910B2C | OK | 96.3 44 0 / 0 | | 0 | 0000:C9:00.0 | 0 0 / 0 3381 / 65536 | +===========================+===============+====================================================+ +---------------------------+---------------+----------------------------------------------------+ | NPU Chip | Process id | Process name | Process memory(MB) | +===========================+===============+====================================================+ | No running processes found in NPU 0 | +===========================+===============+====================================================+ | No running processes found in NPU 1 | +===========================+===============+====================================================+ | No running processes found in NPU 2 | +===========================+===============+====================================================+ | No running processes found in NPU 3 | +===========================+===============+====================================================+ | No running processes found in NPU 4 | +===========================+===============+====================================================+ | No running processes found in NPU 5 | +===========================+===============+====================================================+ | No running processes found in NPU 6 | +===========================+===============+====================================================+ | No running processes found in NPU 7 | +===========================+===============+====================================================+ | No running processes found in NPU 8 | +===========================+===============+====================================================+ | No running processes found in NPU 9 | +===========================+===============+====================================================+ | No running processes found in NPU 10 | +===========================+===============+====================================================+ | No running processes found in NPU 11 | +===========================+===============+====================================================+ | No running processes found in NPU 12 | +===========================+===============+====================================================+ | No running processes found in NPU 13 | +===========================+===============+====================================================+ | No running processes found in NPU 14 | +===========================+===============+====================================================+ | No running processes found in NPU 15 | +===========================+===============+====================================================+ CANN Version: Error: /bin/sh: 1: ascend-dmi: not found ASCEND_HOME: /usr/local/Ascend/ascend-toolkit/latest ASCEND_TOOLKIT_HOME: /usr/local/Ascend/ascend-toolkit/latest LD_LIBRARY_PATH: /usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/lib:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/examples:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/tests/atbopstest:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64/plugin:/usr/local/Ascend/ascend-toolkit/latest/lib64:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/opskernel:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/nnengine:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe/op_tiling/lib/linux/x86_64:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/lib:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/examples:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/tests/atbopstest:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64/plugin:/usr/local/Ascend/ascend-toolkit/latest/lib64:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/opskernel:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/nnengine:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe/op_tiling:/usr/local/Ascend/driver/lib64/common/:/usr/local/Ascend/driver/lib64/driver/: vLLM Info: --------- vLLM Version: 0.9.2 vLLM Ascend Version: Unknown vLLM Custom Ops: Available Environment Variables: --------------------- ATB_OPSRUNNER_KERNEL_CACHE_TILING_SIZE: 10240 ATB_OPSRUNNER_KERNEL_CACHE_LOCAL_COUNT: 1 ATB_STREAM_SYNC_EVERY_RUNNER_ENABLE: 0 ATB_OPSRUNNER_SETUP_CACHE_ENABLE: 1 ATB_WORKSPACE_MEM_ALLOC_GLOBAL: 0 ATB_DEVICE_TILING_BUFFER_BLOCK_NUM: 32 ATB_STREAM_SYNC_EVERY_KERNEL_ENABLE: 0 ATB_OPSRUNNER_KERNEL_CACHE_GLOABL_COUNT: 5 ATB_HOME_PATH: /usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0 ASCEND_TOOLKIT_HOME: /usr/local/Ascend/ascend-toolkit/latest PYTHONPATH: /usr/local/Ascend/ascend-toolkit/latest/python/site-packages:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe:/usr/local/Ascend/ascend-toolkit/latest/python/site-packages:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe: ATB_COMPARE_TILING_EVERY_KERNEL: 0 ASCEND_OPP_PATH: /usr/local/Ascend/ascend-toolkit/latest/opp LD_LIBRARY_PATH: /usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/lib:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/examples:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/tests/atbopstest:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64/plugin:/usr/local/Ascend/ascend-toolkit/latest/lib64:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/opskernel:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/nnengine:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe/op_tiling/lib/linux/x86_64:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/lib:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/examples:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/tests/atbopstest:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64/plugin:/usr/local/Ascend/ascend-toolkit/latest/lib64:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/opskernel:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/nnengine:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe/op_tiling:/usr/local/Ascend/driver/lib64/common/:/usr/local/Ascend/driver/lib64/driver/: ASCEND_AICPU_PATH: /usr/local/Ascend/ascend-toolkit/latest ATB_OPSRUNNER_KERNEL_CACHE_TYPE: 3 ATB_RUNNER_POOL_SIZE: 64 ATB_STREAM_SYNC_EVERY_OPERATION_ENABLE: 0 PATH: /usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/bin:/usr/local/Ascend/ascend-toolkit/latest/bin:/usr/local/Ascend/ascend-toolkit/latest/compiler/ccec_compiler/bin:/usr/local/Ascend/ascend-toolkit/latest/tools/ccec_compiler/bin:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_0/bin:/usr/local/Ascend/ascend-toolkit/latest/bin:/usr/local/Ascend/ascend-toolkit/latest/compiler/ccec_compiler/bin:/usr/local/Ascend/ascend-toolkit/latest/tools/ccec_compiler/bin:/usr/local/python3.10.17/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin ASCEND_HOME_PATH: /usr/local/Ascend/ascend-toolkit/latest ATB_MATMUL_SHUFFLE_K_ENABLE: 1 ATB_LAUNCH_KERNEL_WITH_TILING: 1 ATB_WORKSPACE_MEM_ALLOC_ALG_TYPE: 1 ATB_HOST_TILING_BUFFER_BLOCK_NUM: 128 ATB_SHARE_MEMORY_NAME_SUFFIX: TORCH_DEVICE_BACKEND_AUTOLOAD: 1启动容器的命令如下
docker run -itd \ --device=/dev/davinci0 \ --device=/dev/davinci1 \ --device=/dev/davinci2 \ --device=/dev/davinci3 \ --device=/dev/davinci4 \ --device=/dev/davinci5 \ --device=/dev/davinci6 \ --device=/dev/davinci7 \ --device=/dev/davinci8 \ --device=/dev/davinci9 \ --device=/dev/davinci10 \ --device=/dev/davinci11 \ --device=/dev/davinci12 \ --device=/dev/davinci13 \ --device=/dev/davinci14 \ --device=/dev/davinci15 \ --device=/dev/davinci_manager \ --device=/dev/devmm_svm \ --device=/dev/hisi_hdc \ -v /etc/localtime:/etc/localtime \ -v /usr/local/Ascend/driver:/usr/local/Ascend/driver \ -v /etc/ascend_install.info:/etc/ascend_install.info \ -v /var/log/npu/:/usr/slog \ -v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi \ -v /sys/fs/cgroup:/sys/fs/cgroup:ro \ -v /gpfs/gcsp/:/workspace \ --net=host \ --ipc=host \ --name vllm-0.9.2 \ nexus-docker.zs.shaipower.online/gcsp/vllm-ascend:v0.9.2rc1 \ /bin/bashvllm_demo.py
from vllm import LLM, SamplingParams # Use local model path MODEL_PATH = "/workspace/model/DeepSeek-R1-bf16-hfd-w8a8" # Only need to modify this line prompts = [ "Hello, my name is", "The president of the United States is", "The capital of France is", "The future of AI is", ] # Create sampling parameters sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=128) print(f"Loading model: {MODEL_PATH}...") # Create LLM instance llm = LLM( model=MODEL_PATH, trust_remote_code=True, tensor_parallel_size=16, enforce_eager=True, gpu_memory_utilization=0.8) print("Model loaded successfully, starting text generation...") # Generate text outputs = llm.generate(prompts, sampling_params) print("\nGeneration results:") for output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(f"Prompt: {prompt!r}") print(f"Generated: {generated_text!r}") print("-" * 80) print("Inference completed!")完整的报错信息
ERROR 07-25 15:40:31 [core.py:586] EngineCore failed to start. ERROR 07-25 15:40:31 [core.py:586] Traceback (most recent call last): ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 577, in run_engine_core ERROR 07-25 15:40:31 [core.py:586] engine_core = EngineCoreProc(*args, **kwargs) ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 404, in __init__ ERROR 07-25 15:40:31 [core.py:586] super().__init__(vllm_config, executor_class, log_stats, ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 75, in __init__ ERROR 07-25 15:40:31 [core.py:586] self.model_executor = executor_class(vllm_config) ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/executor/executor_base.py", line 53, in __init__ ERROR 07-25 15:40:31 [core.py:586] self._init_executor() ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/executor/multiproc_executor.py", line 93, in _init_executor ERROR 07-25 15:40:31 [core.py:586] self.workers = WorkerProc.wait_for_ready(unready_workers) ERROR 07-25 15:40:31 [core.py:586] File "/vllm-workspace/vllm/vllm/v1/executor/multiproc_executor.py", line 422, in wait_for_ready ERROR 07-25 15:40:31 [core.py:586] raise e from None ERROR 07-25 15:40:31 [core.py:586] Exception: WorkerProc initialization failed due to an exception in a background process. See stack trace for root cause. Process EngineCore_0: 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, File "/vllm-workspace/vllm/vllm/v1/engine/core.py", line 75, in __init__ self.model_executor = executor_class(vllm_config) File "/vllm-workspace/vllm/vllm/executor/executor_base.py", line 53, in __init__ self._init_executor() File "/vllm-workspace/vllm/vllm/v1/executor/multiproc_executor.py", line 93, in _init_executor self.workers = WorkerProc.wait_for_ready(unready_workers) File "/vllm-workspace/vllm/vllm/v1/executor/multiproc_executor.py", line 422, in wait_for_ready raise e from None Exception: WorkerProc initialization failed due to an exception in a background process. See stack trace for root cause. Traceback (most recent call last): File "/workspace/test/vllm_demo.py", line 42, in <module> main() File "/workspace/test/vllm_demo.py", line 19, in main llm = LLM( File "/vllm-workspace/vllm/vllm/entrypoints/llm.py", line 271, in __init__ self.llm_engine = LLMEngine.from_engine_args( File "/vllm-workspace/vllm/vllm/engine/llm_engine.py", line 501, in from_engine_args return engine_cls.from_vllm_config( File "/vllm-workspace/vllm/vllm/v1/engine/llm_engine.py", line 124, in from_vllm_config return cls(vllm_config=vllm_config, File "/vllm-workspace/vllm/vllm/v1/engine/llm_engine.py", line 101, in __init__ self.engine_core = EngineCoreClient.make_client( File "/vllm-workspace/vllm/vllm/v1/engine/core_client.py", line 75, in make_client return SyncMPClient(vllm_config, executor_class, log_stats) File "/vllm-workspace/vllm/vllm/v1/engine/core_client.py", line 503, in __init__ super().__init__( File "/vllm-workspace/vllm/vllm/v1/engine/core_client.py", line 403, in __init__ with launch_core_engines(vllm_config, executor_class, File "/usr/local/python3.10.17/lib/python3.10/contextlib.py", line 142, in __exit__ next(self.gen) File "/vllm-workspace/vllm/vllm/v1/engine/utils.py", line 434, in launch_core_engines /usr/local/python3.10.17/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 2 leaked shared_memory objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d ' wait_for_engine_startup( File "/vllm-workspace/vllm/vllm/v1/engine/utils.py", line 484, in wait_for_engine_startup raise RuntimeError("Engine core initialization failed. " RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {'EngineCore_0': 1} [ERROR] 2025-07-25-15:40:31 (PID:37468, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception具体的原因应该出现在这几行
File "/vllm-workspace/vllm-ascend/vllm_ascend/quantization/quant_config.py", line 92, in get_quant_method
if self.is_layer_skipped_ascend(prefix,
File "/vllm-workspace/vllm-ascend/vllm_ascend/quantization/quant_config.py", line 137, in is_layer_skipped_ascend
is_skipped = self.quant_description[prefix + '.weight'] == "FLOAT"
KeyError: 'model.layers.0.self_attn.q_a_proj.weight'