PrototypeCommon
Nathanw1014/strix-halo-llamacpp
Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.
- Owner
- Nathanw1014 (personal account)
- Stars
- Stars: 223
- Forks
- Forks: 20
- Language
- Python
- License
- None
- Created
- 2026
- Topics
- amdflash-attentiongfx1151llama-cppllm-inferencelocal-llmradvrocmryzen-ai-maxspeculative-decoding
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- typewriter03/DeskoStars: 223PythonPrototype
- RUC-NLPIR/Agent-WorldStars: 223PythonPrototype
- dk23lhl/termius-mcpStars: 223PythonPrototype
- qgriffith-zz/OpenEatsStars: 223PythonPrototype
- aewallin/openvoronoiStars: 223PythonPrototype
- janosgyerik/bashonelinersStars: 223PythonPrototype