[mchiang]

This is just wrong. Ollama has moved off of llama.cpp and is working with hardware partners to support GGML. https://ollama.com/blog/multimodal-models

[paulsmal]

is it?

https://github.com/ollama/ollama/blob/main/llm/server.go#L79

[mchiang]

we keep it for backwards compatibility - all the newer models are implemented inside Ollama directly

[polotics]

can you substantiate this more? llama.ccp.is also relying on ggml