智能AI
None
RateQuant：通过率失真理论实现最佳混合精度 KV 缓存量化
arXiv:2605.06675v1 Announce Type: new Abstract: Large language models cache all previously computed key-value (KV) pairs
2026-05-11
Fei Zuo, Zikang Zhou, Hao Cong, Xiaoyan Xi, Ho Fai Leung