warpfront /
hipfire
RDNA-native LLM inference engine in Rust.
Updated 12 min ago
Why now
Version v0.4.4 came out on October 27.
+31 stars gained this week
Stars gained each day, last 30 days
Usual pace · 4 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
The README covers AMD-GPU setup in detail: the model downloads run about 15 GB or more, and a 24 GB+ card or Strix Halo system is needed, with smaller models suggested for smaller cards. Usage is through a CLI or an OpenAI-compatible HTTP server.
Summary written by AI from the repository’s description and README.
warpfront / hipfire
View on GitHub(opens in new tab)