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.
6.8k
Stars
440
Forks
62.4
Radar Score
Rising
Momentum
Scoring Breakdown
Impact86.2
Velocity41.9
Health53.1
Growth Metrics
7-Day Stars
+11
30-Day Stars
+79
Acceleration
0.60x
Language
Python
Why it ranks
Steady growth — consistently collecting stars and contributors.