BetaRare
scrya-com/rotorquant
KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.
- Owner
- scrya-com (organization)
- Stars
- Stars: 1,058
- Forks
- Forks: 88
- Language
- Python
- License
- None
- Created
- 2026
- Tier
- Beta (700 to 1,999 ★) What this tier means
Nearby in Python
All Python repos- JiehangXie/PaddleBoBoStars: 1,058PythonBeta
- OpenBMB/RepoAgentStars: 1,058PythonBeta
- zeenie-ai/OpenCompanyStars: 1,058PythonBeta
- debops/debops-toolsStars: 1,058PythonBeta
- jwasham/code-catalog-pythonStars: 1,058PythonBeta
- HRNet/HRNet-Image-ClassificationStars: 1,058PythonBeta