[Feature] Adapt mllama4 to support Vision attention. #8487
Description
Checklist
- 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
- 2. Please use English, otherwise it will be closed.
Motivation
Currently the implementation of vision model in mllama4 is imported from transformers, which may have bad performance. We could implement the modules using sglang's implementation of vision attention
Related resources
No response