DeepSeek-v4.1 Flash: Pushing the Limits of KV Cache Compression

mfiguiere 94 points 7 comments September 17, 2026
zartbot.github.io · View on Hacker News

Discussion Highlights (2 comments)

arikrahman

I am very impressed with the KV Cache Compression work as well as the prefix cacheing making queries converge on practically free.

vivzkestrel

404 on the blog page? https://zartbot.github.io/blog/

Semantic search powered by Rivestack pgvector
6,833 stories · 62,541 chunks indexed