PrototypeCommon
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!!
- Owner
- SergiioB (personal account)
- Stars
- Stars: 191
- Forks
- Forks: 13
- Language
- Python
- License
- MIT
- Created
- 2026
- Topics
- battlemageintel-arcintel-arc-b70intel-gpullama-cppllm-inferencelocal-aimoemtpspeculative-decoding
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- kiyotakali/MiruStars: 191PythonPrototype
- ringlochid/oh-my-subagentsStars: 191PythonPrototype
- Polytutor-AI-Labs/polymarket-black-scholes-hft-botStars: 191PythonPrototype
- coderholic/PyWebShotStars: 191PythonPrototype
- nix-community/pypi2nixStars: 191PythonPrototype
- felinx/d3statusStars: 191PythonPrototype