PrototypeCommon
poisonxa16/pxa
The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; benchmarks vs llama.cpp in the README.
- Owner
- poisonxa16 (personal account)
- Stars
- Stars: 110
- Forks
- Forks: 16
- Language
- C++
- License
- MIT
- Created
- 2026
- Topics
- cudaggufllama-cppp100pascalquantizationspeculative-decodingv100vllmvolta
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in C++
All C++ repos- nolffan/nolfsrcStars: 110C++Prototype
- RanggaCasper/ShaolinMonks-AndroidStars: 110C++Prototype
- xFractals/pokopia-nativeStars: 110C++Prototype
- tomz/libsvm-ruby-swigStars: 110C++Prototype
- kylemcdonald/ofxEdsdkStars: 110C++Prototype
- OP-DSL/OP2-CommonStars: 110C++Prototype