LMSYS：Blog（Chatbot Arena 团队）·· 13 小时前AI 评分46
SGLang 推出 Unified Radix Cache：用一棵基数树统一混合模型前缀缓存
Blog Unified Radix Cache: One Tree for Hybrid Model Prefix Caching Prefix caching reuses KV when requests share the same token prefix. Under full attention, once the KV for a shared prefix is computed, it remains valid as more tokens are appended. A later request wit... Zhangheng Huang, Ke Bao, Yi Zhang, Jialin Ouyang, Sicheng Pan August 11, 2026
AI 导读
SGLang 发布 Unified Radix Cache，用单一 token 基数树统一 full attention KV、滑动窗口 KV 与 Mamba 循环状态的复用边界，替代此前的缓存类矩阵。
来源：LMSYS：Blog（Chatbot Arena 团队） · lmsys.org