search

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
4.42k stars 241 forks source link

Fix (LLMLingua): support mps, fix keep_flag out of dimension. #27

Closed iofu728 closed 8 months ago

iofu728 commented 8 months ago
  1. add support for 'mps' within the device mapping configuration.
  2. correct the calculation for repeats at a coarse level.
  3. resolve the issue where the 'keep_flag' variable exceeds its intended dimensions.