智能AI None 超越TurboQuant!OSCAR:面向真实服务的2-bit KV Cache量化 作者 | Zhongzhu Zhou, Donglin Zhuang, Jisen Li, Ziyan Chen, Shuaiwen Leon Song, Ben Athiwaratkun, Xiaoxia Wu 从 KV Cache 瓶颈 OSCAR attention bit 2026-05-29 Zhongzhu Zhou等