R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration

Open Webpage

Zefan Cai, Wen Xiao, Hanshi Sun, Cheng Luo, Yikai Zhang, Ke Wan, Yucheng Li, Yeyang Zhou, Li-Wen Chang, Jiuxiang Gu, Zhen Dong, Anima Anandkumar, Abedelkadir Asi, Junjie Hu

Published: 2025, Last Modified: 07 Nov 2025CoRR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0