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.
4,812Updated last month

Alternatives and similar repositories for LLMLingua:

Users that are interested in LLMLingua are comparing it to the libraries listed below