Reproduce “DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing” 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

Jinyu Guo, Zhihan Zhang, Jiehui Xie, Md. Tamim Iqbal, Dongshen Han, Lik-Hang Lee, Sung-Ho Bae, Jie Zou and 2 more

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