[Bug]: Qwen2.5-omni Qwen3-omni gradio.py, AsyncOmni.__init__() missing 1 required positional argument: 'cli_args'

[david6666666]

Your current environment

The output of python collect_env.py

Your output of `python collect_env.py` here

🐛 Describe the bug

caused by

• [Bugfix] Support passing vllm cli args to online serving in vLLM-Omni #206

python examples/online_serving/qwen2_5_omni/gradio_demo.py --model /workspace/models/Qwen/Qwen2.5-Omni-7B

log:

INFO 12-09 02:55:52 [__init__.py:216] Automatically detected platform cuda.
Initializing AsyncOmni with model: /workspace/models/Qwen/Qwen2.5-Omni-7B
[AsyncOmni] __del__ close()
Exception ignored in: <function AsyncOmni.__del__ at 0x7f90c10e0cc0>
Traceback (most recent call last):
  File "/workspace/c00580271/cwq_branch/vllm-omni/vllm_omni/entrypoints/async_omni.py", line 196, in __del__
    raise Exception("test")
Exception: test
Traceback (most recent call last):
  File "/workspace/c00580271/cwq_branch/vllm-omni/examples/online_serving/qwen2_5_omni/gradio_demo.py", line 535, in <module>
    main()
  File "/workspace/c00580271/cwq_branch/vllm-omni/examples/online_serving/qwen2_5_omni/gradio_demo.py", line 503, in main
    omni = AsyncOmni(
           ^^^^^^^^^^
TypeError: AsyncOmni.__init__() missing 1 required positional argument: 'cli_args'

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.