Clean-room AGPL-3.0 reimplementation of the halogen 0.1.3 inference engine for Qwen3.8-27B on AMD Strix Halo (gfx1151) — same wire protocol and OpenAI-compatible API. Not affiliated with Peonist.
agpl-3-0
amd-gpu
clean-room
cpp23
gfx1151
halogen
hip
llm-inference
openai-api
qwen3
reimplementation
rocm
strix-halo
Updated 2026-09-10 00:01:30 +00:00