Exact LLM inference engine written from scratch for AMD Strix Halo (gfx1151, ROCm/HIP). Qwen3.8-Flash-Next on one node or two replicas; DeepSeek V4.1 Flash across two nodes over USB4 with an optional RTX PRO. Speculative decoding bit-identical to greedy, up to 255 tok/s on coding chat. MiniMax and GLM next.
What is the hyukudan/strix-halo-engine-lab GitHub project? Description: "Exact LLM inference engine written from scratch for AMD Strix Halo (gfx1151, ROCm/HIP). Qwen3.8-Flash-Next on one node or two replicas; DeepSeek V4.1 Flash across two nodes over USB4 with an optional RTX PRO. Speculative decoding bit-identical to greedy, up to 255 tok/s on coding chat. MiniMax and GLM next.". Written in C++. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
Add it to a GitHub README or profile — the card updates as the ranking changes:
Clone via HTTPS
Clone via SSH
Download ZIP
Download main.zipReport bugs or request features on the strix-halo-engine-lab issue tracker:
Open GitHub Issues