microsoft / LLMLingua

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.
https://llmlingua.com/
MIT License
4.27k stars 228 forks source link

change input parameter from ratio to rate #91

Closed SiyunZhao closed 5 months ago

SiyunZhao commented 5 months ago

Change parameter from ratio to rate. Compression rate = compressed size / raw size (lower is better)