News for hackers. Stuff that matters.
Re:Show HN: We made our own inference engine for Apple Silicon by worldsavior on Tuesday July 15, 2025 @01:32PM (#44573715)
It's utilizing Apple ANE and probably other optimization tools provided by Apple's framework. Not sure if llama.cpp uses them, but if they're not then the benchmark on GitHub says it all.

There are no comments on this comment yet.