Reproduce “PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Weisheng Jin, Maojia Song, Tej Deep Pala, Yew Ken Chia, Amir Zadeh, Chuan Li, Soujanya Poria

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.