GitHub · Shell
peonist-ai/halogen-flash-server
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
- Stars
- 1,403
- Forks
- 101
- Stars gained in 24 hours
- +17
- Forks gained in 24 hours
- +3
Topics: amd, gfx1151, gpu-inference, hip, inference-engine, llm, llm-serving, local-llm, long-context, mixture-of-experts
Latest data point: Nov 20, 2026 · 1,403 stars · 101 forks