Reproduce “Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUs” 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
Zhengxiang Huang, Shengheng Chen, Chaoyue Niu, Yujie Sun, Zhaode Wang, Zeyu Zhao, Chengfei Lv, Fan Wu and 1 more
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.