The Local LLM Index / Inference Engines / #112
SergiioB/intel-arc-pro-b70-inference-cookbook
by SergiioB · Inference Engines · updated 1d ago
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!!
61
momentum
187
stars
12
forks
#112
rank
battlemageintel-arcintel-arc-b70intel-gpullama-cppllm-inferencelocal-aimoemtpspeculative-decodingsyclvllm
View on GitHub →