AlphaUncommon
FMInference/H2O
[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
- Owner
- FMInference (organization)
- Stars
- Stars: 537
- Forks
- Forks: 91
- Language
- Python
- License
- None
- Created
- 2023
- Topics
- gpt-3heavy-hittershigh-throughputkv-cachelarge-language-modelssparsity
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by FMInference
All 3 repos by FMInference- FMInference/FlexLLMGenStars: 9,343PythonStable
- FMInference/DejaVuStars: 363PythonAlpha
Nearby in Python
All Python repos- CerebrasResearch/reapStars: 537PythonAlpha
- ARCANGEL0/MitsuStars: 537PythonAlpha
- lasselian/prism-desktopStars: 537PythonAlpha
- Pymol-Scripts/Pymol-script-repoStars: 537PythonAlpha
- Valloric/MatchTagAlwaysStars: 537PythonAlpha
- benhoyt/scandirStars: 537PythonAlpha