vllm flags missing video_preprocessor_config.json file
(APIServer pid=33439) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=33439) File "/Users/xx/.venv-vllm-metal/lib/python3.12/site-packages/transformers/processing_utils.py", line 1421, in from_pretrained
(APIServer pid=33439) args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, processor_dict, **kwargs)
(APIServer pid=33439) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=33439) File "/Users/xx/.venv-vllm-metal/lib/python3.12/site-packages/transformers/processing_utils.py", line 1550, in _get_arguments_from_pretrained
(APIServer pid=33439) sub_processor = auto_processor_class.from_pretrained(
(APIServer pid=33439) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=33439) File "/Users/xx/.venv-vllm-metal/lib/python3.12/site-packages/transformers/models/auto/video_processing_auto.py", line 331, in from_pretrained
(APIServer pid=33439) config_dict, _ = BaseVideoProcessor.get_video_processor_dict(pretrained_model_name_or_path, **kwargs)
(APIServer pid=33439) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=33439) File "/Users/xx/.venv-vllm-metal/lib/python3.12/site-packages/transformers/video_processing_utils.py", line 676, in get_video_processor_dict
(APIServer pid=33439) raise OSError(
(APIServer pid=33439) OSError: Can't load video processor for 'mlx-community/gemma-4-e4b-it-4bit'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'mlx-community/gemma-4-e4b-it-4bit' is the correct path to a directory containing a video_preprocessor_config.json file