asf0/libstrix
HIP kernels for AMD Strix Halo (gfx1151) and a vLLM plugin that runs them on stock upstream vLLM: up to 31x faster prefill and ~2x decode at long context.
GitHub repository with 17 stars and 1 forks.
Language: Python
Topics: amd, gfx1151, hip, llm-inference, rocm, strix-halo, vllm