Episode Details
Back to EpisodesShrinking Language Model Hints for Speed
Episode 135
Published 2 years, 6 months ago
Description
This podcast was created entirely by AI and based on the following research paper:
- Title: LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
- Source: arXiv
- Authors: Huiqiang Jiang et al.
- Published Date: 2023-12-06
Visit www.paper2podcast.com to download the full paper and learn more. Thanks for listening!