Reproduce “Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving” 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
Hui Zeng, Daming Zhao, Pengfei Yang, WenXuan Hou, Tianyang Zheng, Hui Li, Weiye Ji, Jidong Zhai
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.