300duo的服务器 vllm部署qwen3时报错,请大佬帮忙解决
收藏回复举报
300duo的服务器 vllm部署qwen3时报错,请大佬帮忙解决
t('forum.solved') 已解决
发表于2025-08-14 18:12:27
0 查看

ERROR 08-14 09:42:11 engine.py:400] SetPrecisionMode:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:155 NPU function error: at_npu::native::AclSetCompileopt(aclCompileOpt::ACL_PRECISION_MODE, precision_mode), error code is 500001

ERROR 08-14 09:42:11 engine.py:400] [ERROR] 2025-08-14-09:42:11 (PID:7401, Device:0, RankID:-1) ERR00100 PTA call acl api failed

ERROR 08-14 09:42:11 engine.py:400] [Error]: The internal ACL of the system is incorrect.

ERROR 08-14 09:42:11 engine.py:400]         Rectify the fault based on the error information in the ascend log.

ERROR 08-14 09:42:11 engine.py:400] E19999: Inner Error!

ERROR 08-14 09:42:11 engine.py:400] E19999: [PID: 7401] 2025-08-14-09:42:11.573.461 GELib::InnerInitialize failed.[FUNC:Initialize][FILE:gelib.cc][LINE:164]

ERROR 08-14 09:42:11 engine.py:400]         TraceBack (most recent call last):

ERROR 08-14 09:42:11 engine.py:400]        GEInitialize failed.[FUNC:GEInitialize][FILE:ge_api.cc][LINE:382]

ERROR 08-14 09:42:11 engine.py:400]        [Initialize][Ge]GEInitialize failed. ge result = 4294967295[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]

ERROR 08-14 09:42:11 engine.py:400]        [Init][Compiler]Init compiler failed[FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]

ERROR 08-14 09:42:11 engine.py:400]        [Set][Options]OpCompileProcessor init failed![FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]

ERROR 08-14 09:42:11 engine.py:400] Traceback (most recent call last):

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 391, in run_mp_engine

ERROR 08-14 09:42:11 engine.py:400]     engine = MQLLMEngine.from_engine_args(engine_args=engine_args,

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 124, in from_engine_args

ERROR 08-14 09:42:11 engine.py:400]     return cls(ipc_path=ipc_path,

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 76, in __init__

ERROR 08-14 09:42:11 engine.py:400]     self.engine = LLMEngine(*args, **kwargs)

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 273, in __init__

ERROR 08-14 09:42:11 engine.py:400]     self.model_executor = executor_class(vllm_config=vllm_config, )

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/executor/executor_base.py", line 271, in __init__

ERROR 08-14 09:42:11 engine.py:400]     super().__init__(*args, **kwargs)

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/executor/executor_base.py", line 52, in __init__

ERROR 08-14 09:42:11 engine.py:400]     self._init_executor()

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/executor/mp_distributed_executor.py", line 124, in _init_executor

ERROR 08-14 09:42:11 engine.py:400]     self._run_workers("init_device")

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/executor/mp_distributed_executor.py", line 185, in _run_workers

ERROR 08-14 09:42:11 engine.py:400]     driver_worker_output = run_method(self.driver_worker, sent_method,

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/utils.py", line 2196, in run_method

ERROR 08-14 09:42:11 engine.py:400]     return func(*args, **kwargs)

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm_ascend/worker/worker.py", line 183, in init_device

ERROR 08-14 09:42:11 engine.py:400]     NPUPlatform.set_device(self.device)

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm_ascend/platform.py", line 90, in set_device

ERROR 08-14 09:42:11 engine.py:400]     torch.npu.set_device(device)

ERROR 08-14 09:42:11 engine.py:400]   File "/data/conda_env/vllm/lib/python3.10/site-packages/torch_npu/npu/utils.py", line 83, in set_device

ERROR 08-14 09:42:11 engine.py:400]     torch_npu._C._npu_setDevice(device_id)

ERROR 08-14 09:42:11 engine.py:400] RuntimeError: SetPrecisionMode:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:155 NPU function error: at_npu::native::AclSetCompileopt(aclCompileOpt::ACL_PRECISION_MODE, precision_mode), error code is 500001

ERROR 08-14 09:42:11 engine.py:400] [ERROR] 2025-08-14-09:42:11 (PID:7401, Device:0, RankID:-1) ERR00100 PTA call acl api failed

ERROR 08-14 09:42:11 engine.py:400] [Error]: The internal ACL of the system is incorrect.

ERROR 08-14 09:42:11 engine.py:400]         Rectify the fault based on the error information in the ascend log.

ERROR 08-14 09:42:11 engine.py:400] E19999: Inner Error!

ERROR 08-14 09:42:11 engine.py:400] E19999: [PID: 7401] 2025-08-14-09:42:11.573.461 GELib::InnerInitialize failed.[FUNC:Initialize][FILE:gelib.cc][LINE:164]

ERROR 08-14 09:42:11 engine.py:400]         TraceBack (most recent call last):

ERROR 08-14 09:42:11 engine.py:400]        GEInitialize failed.[FUNC:GEInitialize][FILE:ge_api.cc][LINE:382]

ERROR 08-14 09:42:11 engine.py:400]        [Initialize][Ge]GEInitialize failed. ge result = 4294967295[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]

ERROR 08-14 09:42:11 engine.py:400]        [Init][Compiler]Init compiler failed[FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]

ERROR 08-14 09:42:11 engine.py:400]        [Set][Options]OpCompileProcessor init failed![FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]

ERROR 08-14 09:42:11 engine.py:400] 

ERROR 08-14 09:42:11 multiproc_worker_utils.py:124] Worker VllmWorkerProcess pid 7859 died, exit code: -15

INFO 08-14 09:42:11 multiproc_worker_utils.py:128] Killing local vLLM worker processes

Process SpawnProcess-1:

Traceback (most recent call last):

  File "/data/conda_env/vllm/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap

    self.run()

  File "/data/conda_env/vllm/lib/python3.10/multiprocessing/process.py", line 108, in run

    self._target(*self._args, **self._kwargs)

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 402, in run_mp_engine

    raise e

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 391, in run_mp_engine

    engine = MQLLMEngine.from_engine_args(engine_args=engine_args,

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 124, in from_engine_args

    return cls(ipc_path=ipc_path,

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 76, in __init__

    self.engine = LLMEngine(*args, **kwargs)

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 273, in __init__

    self.model_executor = executor_class(vllm_config=vllm_config, )

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/executor/executor_base.py", line 271, in __init__

    super().__init__(*args, **kwargs)

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/executor/executor_base.py", line 52, in __init__

    self._init_executor()

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/executor/mp_distributed_executor.py", line 124, in _init_executor

    self._run_workers("init_device")

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/executor/mp_distributed_executor.py", line 185, in _run_workers

    driver_worker_output = run_method(self.driver_worker, sent_method,

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/utils.py", line 2196, in run_method

    return func(*args, **kwargs)

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm_ascend/worker/worker.py", line 183, in init_device

    NPUPlatform.set_device(self.device)

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm_ascend/platform.py", line 90, in set_device

    torch.npu.set_device(device)

  File "/data/conda_env/vllm/lib/python3.10/site-packages/torch_npu/npu/utils.py", line 83, in set_device

    torch_npu._C._npu_setDevice(device_id)

RuntimeError: SetPrecisionMode:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:155 NPU function error: at_npu::native::AclSetCompileopt(aclCompileOpt::ACL_PRECISION_MODE, precision_mode), error code is 500001

[ERROR] 2025-08-14-09:42:11 (PID:7401, 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.

E19999: Inner Error!

E19999: [PID: 7401] 2025-08-14-09:42:11.573.461 GELib::InnerInitialize failed.[FUNC:Initialize][FILE:gelib.cc][LINE:164]

        TraceBack (most recent call last):

       GEInitialize failed.[FUNC:GEInitialize][FILE:ge_api.cc][LINE:382]

       [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]

/data/conda_env/vllm/lib/python3.10/tempfile.py:869: ResourceWarning: Implicitly cleaning up <TemporaryDirectory '/tmp/tmpz1wg1925'>

  _warnings.warn(warn_message, ResourceWarning)

sys:1: DeprecationWarning: builtin type swigvarlink has no __module__ attribute

Traceback (most recent call last):

  File "/data/conda_env/vllm/bin/vllm", line 8, in <module>

    sys.exit(main())

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/entrypoints/cli/main.py", line 73, in main

    args.dispatch_function(args)

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/entrypoints/cli/serve.py", line 34, in cmd

    uvloop.run(run_server(args))

  File "/data/conda_env/vllm/lib/python3.10/site-packages/uvloop/__init__.py", line 82, in run

    return loop.run_until_complete(wrapper())

  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete

  File "/data/conda_env/vllm/lib/python3.10/site-packages/uvloop/__init__.py", line 61, in wrapper

    return await main

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 947, in run_server

    async with build_async_engine_client(args) as engine_client:

  File "/data/conda_env/vllm/lib/python3.10/contextlib.py", line 199, in __aenter__

    return await anext(self.gen)

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 139, in build_async_engine_client

    async with build_async_engine_client_from_engine_args(

  File "/data/conda_env/vllm/lib/python3.10/contextlib.py", line 199, in __aenter__

    return await anext(self.gen)

  File "/data/conda_env/vllm/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 233, in build_async_engine_client_from_engine_args

    raise RuntimeError(

RuntimeError: Engine process failed to start. See stack trace for the root cause.

[ERROR] 2025-08-14-09:42:12 (PID:7269, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception

我要发帖子