Open Issues Need Help
View All on GitHub Collect Alchemist and Lunar Lake test reports 17 days ago
help wanted untested 1.0
offbyonebit/arc-llama 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.
Open project →
12
Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.
Python
#alchemist#battlemage#inference#intel-arc#llama-cpp#llm#oneapi#openai-api#sycl
Test multi-GPU swap policy on a 2+ Arc system 19 days ago
enhancement help wanted untested post-1.0
offbyonebit/arc-llama 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.
Open project →
12
Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.
Python
#alchemist#battlemage#inference#intel-arc#llama-cpp#llm#oneapi#openai-api#sycl