AlphaUncommon
jy-yuan/KIVI
[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- Owner
- jy-yuan (personal account)
- Stars
- Stars: 438
- Forks
- Forks: 57
- Language
- Python
- License
- MIT
- Created
- 2024
- Topics
- inferencelarge-language-modelsllamallmnatural-language-processingquantizationtransformer
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in Python
All Python repos- chi2liu/ABC-GRPOStars: 438PythonAlpha
- blessonism/search-skillsStars: 438PythonAlpha
- guilyx/gripStars: 438PythonAlpha
- furious-luke/django-addressStars: 438PythonAlpha
- jvantuyl/sublime_diagram_pluginStars: 438PythonAlpha
- emanuele/kaggle_pbrStars: 438PythonAlpha