←back to thread

Show HN: We made our own inference engine for Apple Silicon

(github.com)
186 points darkolorin | 1 comments | 15 Jul 25 11:29 UTC | HN request time: 0.297s | source

We wrote our inference engine on Rust, it is faster than llama cpp in all of the use cases. Your feedback is very welcomed. Written from scratch with idea that you can add support of any kernel and platform.
1. slavasmirnov ◴[15 Jul 25 14:42 UTC] No.44571641[source]▶
that’s exactly we are looking for not to waste on apis. Wonder how significant trade offs are