Skip to content
Yihua Zhang
Articles
Posts
EN
中
◐
All
KV-Cache
1 article
2025-02-02
Why Cache 32 Heads When One Latent Variable Suffices? A Theory-to-Code Guide to DeepSeek’s MLA for KV-Cache
Systems
·
en / zh
·
24 equations
Anatomy of DeepSeek 2
KV-Cache