Menu

#FRatePietro

1 post

Feed
1 of 1 post
📰
23

Ferrox: Building a Rust Inference Engine That Matches llama.cpp

Hacker News·2 months ago
#XqbMNFIk
#fratepietro#llama#ferrox#metal#gguf#models

Why I built Ferrox, a pure-Rust GGUF inference engine, and what it took to match llama.cpp’s performance on real models — with receipts, not vibes.

15s
Read More