Illustration: the project’s public image, pixelated by RepoMasters. Credits
StableVery rare

microsoft/LLMLingua

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Owner
microsoft (organization)
Stars
Stars: 6,795
Forks
Forks: 448
Language
Python
License
MIT
Created
2023
Tier
Stable (5,000 to 19,999 ★) What this tier means
View on GitHub

More repos by microsoft

All 1,923 repos by microsoft

Nearby in Python

All Python repos