support for llama3.2 vision

[ahmedBouchaibi]

First of all thanks for the amazing work.
is any plan to support LLama3.2 vision models or QwenVL models

[mikepapadim]

Hello @ahmedBouchaibi ,

Currently, we only working on Text-Only LLMs.
It will take as some time to support multi-modal models for text to image generation as in llama3.2 vision