offbyonebit/arc-llama
Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.
GitHub repository with 12 stars and 1 forks.
Language: Python
Topics: alchemist, battlemage, inference, intel-arc, llama-cpp, llm, oneapi, openai-api, sycl