LLaMA Now Goes Faster on CPUs | Hacker News - But Better

LLaMA Now Goes Faster on CPUs justine.lol

I wrote 84 new matmul kernels to improve llamafile CPU performance.

1 points•luu•about 6 hours ago•0 comments•

#llama #cpus #faster #goes faster #matmul #wrote #improve #kernels

0 comments

No comments yet.

Related stories

Faster prompt lookup drafting in llama.cppjadidbourbaki.github.io
Hacker News · 70 points · 6 days ago
The Next 3x in Inference Won't Come from Faster Kernelstwitter.com
Hacker News · 2 points · 3 days ago
I Wrote The Fastest Hashtableprobablydance.com
Lobsters · 4 points · over 9 years ago
Show HN: Droid ASC – An On-Demand Android Decompiler, 41–269x Faster Than JADXgithub.com
Hacker News · 2 points · 9 days ago
Writing Rust code faster than SotA by asking agents to make the code fasterminimaxir.com
Hacker News · 1 points · 11 days ago
Writing Rust code that's faster than state-of-the-art libraries by asking agents to make the code fasterminimaxir.com
Lobsters · 5 points · 10 days ago