GitHub · Python
asf0/libstrix
Fast vLLM on AMD Strix Halo: one docker command for Qwen, Gemma, LFM and more, up to 31x faster prefill and ~2x decode vs stock vLLM at long context.
- Stars
- 23
- Forks
- 1
- Stars gained in 24 hours
- +4
- Forks gained in 24 hours
- 0
Topics: amd, docker, framework-desktop, gemma, gfx1151, hip, inference, inference-optimization, llm-inference, local-llm
Latest data point: Nov 22, 2026 · 23 stars · 1 forks