< cd ../gallery
[AI & ML]
intel-arc-pro-b70-inference-cookbook
Open recipes, engine patches, and benchmark harnesses for LLM inference on Intel Arc Pro B60/B70 (Battlemage, Xe2). MoE 35B at 126 t/s decode / 7.5K t/s prefill single-stream — vLLM XPU MTP unlocked.
@SergiioB
maintainer
★ 16 stars
# README
Open recipes, engine patches, and benchmark harnesses for LLM inference on Intel Arc Pro B60/B70 (Battlemage, Xe2). MoE 35B at 126 t/s decode / 7.5K t/s prefill single-stream — vLLM XPU MTP unlocked. Maintained by SergiioB on GitHub, where it has earned 16 stars from the community.
It's actively developed around battlemage, intel-arc, intel-arc-b70, and is a solid reference for anyone building with these tools.
# tags
# install
npm install intel-arc-pro-b70-inference-cookbookmore vLLM repos
