[Usage]: How should I use the CPU to deploy QWEN3 VL 30B-A3B?

[maxgameone]

Your current environment

The output of `python collect_env.py`

(APIServer pid=1033476) Traceback (most recent call last):
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/bin/vllm", line 33, in
(APIServer pid=1033476) sys.exit(load_entry_point('vllm==0.11.1rc6.dev33+g3a5de7d2d.cpu', 'console_scripts', 'vllm')())
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/entrypoints/cli/main.py", line 73, in main
(APIServer pid=1033476) args.dispatch_function(args)
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/entrypoints/cli/serve.py", line 59, in cmd
(APIServer pid=1033476) uvloop.run(run_server(args))
(APIServer pid=1033476) File "/home/maxgameone/.local/lib/python3.12/site-packages/uvloop/init.py", line 109, in run
(APIServer pid=1033476) return __asyncio.run(
(APIServer pid=1033476) ^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/asyncio/runners.py", line 194, in run
(APIServer pid=1033476) return runner.run(main)
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/asyncio/runners.py", line 118, in run
(APIServer pid=1033476) return self._loop.run_until_complete(task)
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(APIServer pid=1033476) File "/home/maxgameone/.local/lib/python3.12/site-packages/uvloop/init.py", line 61, in wrapper
(APIServer pid=1033476) return await main
(APIServer pid=1033476) ^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/entrypoints/openai/api_server.py", line 1910, in run_server
(APIServer pid=1033476) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/entrypoints/openai/api_server.py", line 1926, in run_server_worker
(APIServer pid=1033476) async with build_async_engine_client(
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/contextlib.py", line 210, in aenter
(APIServer pid=1033476) return await anext(self.gen)
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/entrypoints/openai/api_server.py", line 185, in build_async_engine_client
(APIServer pid=1033476) async with build_async_engine_client_from_engine_args(
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/contextlib.py", line 210, in aenter
(APIServer pid=1033476) return await anext(self.gen)
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/entrypoints/openai/api_server.py", line 232, in build_async_engine_client_from_engine_args
(APIServer pid=1033476) async_llm = AsyncLLM.from_vllm_config(
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/utils/func_utils.py", line 116, in inner
(APIServer pid=1033476) return fn(*args, **kwargs)
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/v1/engine/async_llm.py", line 218, in from_vllm_config
(APIServer pid=1033476) return cls(
(APIServer pid=1033476) ^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/v1/engine/async_llm.py", line 140, in init
(APIServer pid=1033476) self.engine_core = EngineCoreClient.make_async_mp_client(
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/v1/engine/core_client.py", line 121, in make_async_mp_client
(APIServer pid=1033476) return AsyncMPClient(*client_args)
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/v1/engine/core_client.py", line 808, in init
(APIServer pid=1033476) super().init(
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/v1/engine/core_client.py", line 469, in init
(APIServer pid=1033476) with launch_core_engines(vllm_config, executor_class, log_stats) as (
(APIServer pid=1033476) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/contextlib.py", line 144, in exit
(APIServer pid=1033476) next(self.gen)
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/v1/engine/utils.py", line 898, in launch_core_engines
(APIServer pid=1033476) wait_for_engine_startup(
(APIServer pid=1033476) File "/home/maxgameone/anaconda3/lib/python3.12/site-packages/vllm-0.11.1rc6.dev33+g3a5de7d2d.cpu-py3.12-linux-x86_64.egg/vllm/v1/engine/utils.py", line 955, in wait_for_engine_startup
(APIServer pid=1033476) raise RuntimeError(
(APIServer pid=1033476) RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}
(base) maxgameone@zsi-cloud:/home/data/visionlink$ /home/maxgameone/anaconda3/lib/python3.12/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown

How would you like to use vllm

I want to run inference of a [specific model](put link here). I don't know how to integrate it with vllm.

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.