Reproduce “Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA” 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

Nils Graef, Kayvan Zahiri, Andrew Wasielewski

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