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
4.49k stars 251 forks source link

version 0.2.1 iteration plan #110

Closed iofu728 closed 6 months ago

iofu728 commented 6 months ago

Estimated Release Date: 3/19 Release Manager: @suiguoxin Schedule:

Features

Backlog

iofu728 commented 6 months ago

v0.2.1 released. move to v0.2.2.