PrototypeCommon
arozanov/turboquant-mlx
TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.
- Owner
- arozanov (personal account)
- Stars
- Stars: 114
- Forks
- Forks: 19
- Language
- Python
- License
- None
- Created
- 2026
- Topics
- apple-siliconkv-cachellmmetalmlxquantizationturboquant
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- dinosn/php-cve-2026-10961x-lab-pocStars: 114PythonPrototype
- Toyaspio/maibot-baidu-searchStars: 114PythonPrototype
- CumulusAlpha/Dex-SupermimicStars: 114PythonPrototype
- leah/django-elsewhereStars: 114PythonPrototype
- fschulze/mr.developerStars: 114PythonPrototype
- cloudkick/libcloudStars: 114PythonPrototype