Reproduce “Paged Attention Meets FlexAttention: Unlocking Long-Context Efficiency in Deployed 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
Thomas Joshi, Herman Saini, Neil Dhillon, Antoni Viros i Martin, Kaoutar El Maghraoui
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.