PU
Pushing the Limits of KV Cache Compression · zartbot
Author ProfileClaim This Author Profile
Prove ownership by publishing #HashtagPLUS and this profile link on your author page or an article under your byline. A moderator or admin will review the request before it merges into your real HashtagPLUS username.
0 karma0 postsjoined about 3 hours ago
🌐 zartbot.github.ioSource
A deep dive into the DeepSeek-V4.1 Flash technical report: CED, CSA2, HSI, Single-Pass mHC, Engram and FP4 KV Cache — how the KV cache was compressed to just 890 bytes per token.
about 3 hours ago