LightLLM supports Multimodal llm, when will lorax?

[Trickster85]

Model description

https://github.com/ModelTC/lightllm/pull/266

Will there be vision llm support in Lorax soon?

Open source status

• [X] The model implementation is available
• [X] The model weights are available

Provide useful links for the implementation

https://github.com/ModelTC/lightllm/pull/266

[tgaddair]

Hey @Trickster85, yes, we definitely have support for VLMs planned (#179).

There are a few big items we want to get to first including speculative decoding, prefix caching, and embedding endpoints. Once those are done, we do plan on tackling VLMs, but definitely welcome contributions if folks want to take this on before then.