Super simple Python connectors for llama.cpp, including vision models (Gemma 3, Qwen2-VL)

[fidecastro]

I built llama-cpp-connector as a lightweight alternative to llama-cpp-python/Ollama that stays current with llama.cpp's latest releases and enables Python integration with llama.cpp's vision models.

Those of us that use llama.cpp with Python know the angst of waiting for updates of llama.cpp to show up in more Python-friendly backends... I hope this is useful to you as much as it is to me.

https://github.com/fidecastro/llama-cpp-connector