[Feature]: GGUF model with architecture qwen3vlmoe is not supported yet.

[ivanbaldo]

🚀 The feature, motivation and pitch

In 0.11.1rc7.dev109+gca00b1bfc and 0.11.0 we can't use models--Qwen--Qwen3-VL-30B-A3B-Instruct-GGUF/snapshots/f54435e6cc31258f04b0969105c3f6badb197931/Qwen3VL-30B-A3B-Instruct-Q4_K_M.gguf (in a RTX-5090 just in case).

Alternatives

No response

Additional context

[llm]        | (APIServer pid=1) Traceback (most recent call last):
[llm]        | (APIServer pid=1)   File "/usr/local/bin/vllm", line 10, in <module>
[llm]        | (APIServer pid=1)     sys.exit(main())
[llm]        | (APIServer pid=1)              ^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/main.py", line 73, in main
[llm]        | (APIServer pid=1)     args.dispatch_function(args)
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/serve.py", line 59, in cmd
[llm]        | (APIServer pid=1)     uvloop.run(run_server(args))
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 96, in run
[llm]        | (APIServer pid=1)     return __asyncio.run(
[llm]        | (APIServer pid=1)            ^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/lib/python3.12/asyncio/runners.py", line 195, in run
[llm]        | (APIServer pid=1)     return runner.run(main)
[llm]        | (APIServer pid=1)            ^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
[llm]        | (APIServer pid=1)     return self._loop.run_until_complete(task)
[llm]        | (APIServer pid=1)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 48, in wrapper
[llm]        | (APIServer pid=1)     return await main
[llm]        | (APIServer pid=1)            ^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 1944, in run_server
[llm]        | (APIServer pid=1)     await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 1963, in run_server_worker
[llm]        | (APIServer pid=1)     async with build_async_engine_client(
[llm]        | (APIServer pid=1)                ^^^^^^^^^^^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
[llm]        | (APIServer pid=1)     return await anext(self.gen)
[llm]        | (APIServer pid=1)            ^^^^^^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 192, in build_async_engine_client
[llm]        | (APIServer pid=1)     async with build_async_engine_client_from_engine_args(
[llm]        | (APIServer pid=1)                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
[llm]        | (APIServer pid=1)     return await anext(self.gen)
[llm]        | (APIServer pid=1)            ^^^^^^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 218, in build_async_engine_client_from_engine_args
[llm]        | (APIServer pid=1)     vllm_config = engine_args.create_engine_config(usage_context=usage_context)
[llm]        | (APIServer pid=1)                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 1317, in create_engine_config
[llm]        | (APIServer pid=1)     maybe_override_with_speculators(
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/vllm/transformers_utils/config.py", line 530, in maybe_override_with_speculators
[llm]        | (APIServer pid=1)     config_dict, _ = PretrainedConfig.get_config_dict(
[llm]        | (APIServer pid=1)                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/transformers/configuration_utils.py", line 662, in get_config_dict
[llm]        | (APIServer pid=1)     config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
[llm]        | (APIServer pid=1)                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/transformers/configuration_utils.py", line 753, in _get_config_dict
[llm]        | (APIServer pid=1)     config_dict = load_gguf_checkpoint(resolved_config_file, return_tensors=False)["config"]
[llm]        | (APIServer pid=1)                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[llm]        | (APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/transformers/modeling_gguf_pytorch_utils.py", line 431, in load_gguf_checkpoint
[llm]        | (APIServer pid=1)     raise ValueError(f"GGUF model with architecture {architecture} is not supported yet.")
[llm]        | (APIServer pid=1) ValueError: GGUF model with architecture qwen3vlmoe is not supported yet.

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.