vllm-ascend运行Qwen3-Next-80B出错
收藏回复举报
vllm-ascend运行Qwen3-Next-80B出错
t('forum.solved') 已解决
发表于2025-10-29 09:12:42
0 查看
(APIServer pid=565) Traceback (most recent call last):
(APIServer pid=565) File "/usr/local/python3.11.13/bin/vllm", line 8, in
(APIServer pid=565) sys.exit(main())
(APIServer pid=565) ^^^^^^
(APIServer pid=565) File "/vllm-workspace/vllm/vllm/entrypoints/cli/main.py", line 54, in main
(APIServer pid=565) args.dispatch_function(args)
(APIServer pid=565) File "/vllm-workspace/vllm/vllm/entrypoints/cli/serve.py", line 57, in cmd
(APIServer pid=565) uvloop.run(run_server(args))
(APIServer pid=565) File "/usr/local/python3.11.13/lib/python3.11/site-packages/uvloop/init.py", line 105, in run
(APIServer pid=565) return runner.run(wrapper())
(APIServer pid=565) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=565) File "/usr/local/python3.11.13/lib/python3.11/asyncio/runners.py", line 118, in run
(APIServer pid=565) return self._loop.run_until_complete(task)
(APIServer pid=565) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=565) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(APIServer pid=565) File "/usr/local/python3.11.13/lib/python3.11/site-packages/uvloop/init.py", line 61, in wrapper
(APIServer pid=565) return await main
(APIServer pid=565) ^^^^^^^^^^
(APIServer pid=565) File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 1884, in run_server
(APIServer pid=565) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
(APIServer pid=565) File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 1902, in run_server_worker
(APIServer pid=565) async with build_async_engine_client(
(APIServer pid=565) File "/usr/local/python3.11.13/lib/python3.11/contextlib.py", line 210, in aenter
(APIServer pid=565) return await anext(self.gen)
(APIServer pid=565) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=565) File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 180, in build_async_engine_client
(APIServer pid=565) async with build_async_engine_client_from_engine_args(
(APIServer pid=565) File "/usr/local/python3.11.13/lib/python3.11/contextlib.py", line 210, in aenter
(APIServer pid=565) return await anext(self.gen)
(APIServer pid=565) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=565) File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 206, in build_async_engine_client_from_engine_args
(APIServer pid=565) vllm_config = engine_args.create_engine_config(usage_context=usage_context)
(APIServer pid=565) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=565) File "/vllm-workspace/vllm/vllm/engine/arg_utils.py", line 1431, in create_engine_config
(APIServer pid=565) config = VllmConfig(
(APIServer pid=565) ^^^^^^^^^^^
(APIServer pid=565) File "/usr/local/python3.11.13/lib/python3.11/site-packages/pydantic/_internal/_dataclasses.py", line 123, in init
(APIServer pid=565) s.pydantic_validator.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
(APIServer pid=565) File "/vllm-workspace/vllm/vllm/config/init.py", line 306, in post_init
(APIServer pid=565) self.try_verify_and_update_config()
(APIServer pid=565) File "/vllm-workspace/vllm/vllm/config/init.py", line 642, in try_verify_and_update_config
(APIServer pid=565) HybridAttentionMambaModelConfig.verify_and_update_config(self)
(APIServer pid=565) File "/vllm-workspace/vllm-ascend/vllm_ascend/patch/platform/patch_common/patch_mamba_config.py", line 27, in verify_and_update_config
(APIServer pid=565) ascend_config = get_ascend_config()
(APIServer pid=565) ^^^^^^^^^^^^^^^^^^^
(APIServer pid=565) File "/vllm-workspace/vllm-ascend/vllm_ascend/ascend_config.py", line 199, in get_ascend_config
(APIServer pid=565) raise RuntimeError(
(APIServer pid=565) RuntimeError: Ascend config is not initialized. Please call init_ascend_config first.
(APIServer pid=565) [ERROR] 2025-09-30-05:07:51 (PID:565, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception

我要发帖子