llama.cpp will be supported?

[GermanAizek]

@soramimi,

https://github.com/ggml-org/llama.cpp

https://en.wikipedia.org/wiki/Llama.cpp

Ollama is frontend over llama.cpp

In fact, llama.cpp is both library or client/server framework for running local models, the most important advantage compared to Ollama is performance and more supported models.

[soramimi]

My impression is that the local LLM is still underpowered for generating commit messages.

Ollama and LM Studio have experimental support, but I think we'll see how this goes for the time being.

At this point, I don't think we've reached the point where the Guitar directly supports llama.cpp.