Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Ollama is not a wrapper around llama.cpp anymore, at least for multimodal models (not sure about others). They have their own engine: https://ollama.com/blog/multimodal-models


looks like the backend is ggml, am I missing something? same diff




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: