[Usage]: Can it support using the siglip model as the vision model in a multimodal model?

[BrenchCC]

Your current environment

The output of `python collect_env.py`

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.

[jeejeelee]

FYI: #6942

[ywang96]

Just as a reference, generally speaking, you're welcome to import any ViT directly from transformers if the VLM utilizes it (but it would be also great if you port the ViT over)

[BrenchCC]

Thank you so much.