Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

Please support moondream2 model in mtmd

moondream2 is a small vlm that is incredibly good for its small size: https://huggingface.co/vikhyatk/moondream2/

I believe that an earlier version of moondream was supported by llama.cpp at some point, but newer versions are not.

Motivation

moondream2 is one of the best models for memory constrained scenarios such as the edge. adding llama.cpp support will enable inference with vulkan, which is currently lacking.

Possible Implementation

No response