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.
- ATK
- 6263
- DEF
- 3895
Uncommon
microsoft/LLMLingua
Uncommon · Base · Genesis[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.
Attack6,263
Defense3,895
Drag the card to turn it. Use the flip button to see the back.
Open card page