SergiioB/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 160 t/s decode / 7.5K t/s prefill single-stream, 27B at 50~ t/s decode / 1.7K t/s prefill single stream. vLLM XPU MTP unlocked. Muse Glimmer recipe added!!

语言：Python · GitHub 星标：189 · Fork：13

话题：battlemage · intel-arc · intel-arc-b70 · intel-gpu · llama-cpp · llm-inference · local-ai · moe

在 GitHub 上查看原仓库