https://yiwen-cai.github.io/tags/mla/Recent content in MLA on Yiwen CaiHugo -- gohugo.iozh-cncaiyiwen.cs@foxmail.com (Yiwen Cai)caiyiwen.cs@foxmail.com (Yiwen Cai)© 2026 Yiwen CaiFri, 10 Jul 2026 22:20:09 +0800https://yiwen-cai.github.io/notes/llm-inference/kv-cache-optimization-survey/Fri, 10 Jul 2026 00:00:00 +0000caiyiwen.cs@foxmail.com (Yiwen Cai)https://yiwen-cai.github.io/notes/llm-inference/kv-cache-optimization-survey/以 KV Cache Size = 2×L×T×H_kv×D_h×bytes 为锚点，系统梳理 2023–2026 年 KV Cache 优化全景：PagedAttention 与 KV-aware serving 的系统管理、DapQ/LaProx/TurboQuant/LongFlow 等压缩新方法、MHA→MLA→DeepSeek V4 CSA/HCA→GDN→MLRA 的架构演进，并讲清四条路线（压维度/压序列/少访问/固定状态）的边界。