News for hackers. Stuff that matters.

A comment on Show HN: We made our own inference engine for Apple Silicon. Parent comment

Re:Show HN: We made our own inference engine for Apple Silicon by imtringued on Wednesday July 16, 2025 @02:00AM (#44579160)
Actually, ollama has stopped using llama.cpp and is using ggml directly nowadays.
[ Parent | on HN ]

There are no comments on this comment yet.