‹ BackHN Continuity

Thread

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

131 points · 10 comments · mfiguiere

  1. arikrahman · · focus · HN ↗
    I am very impressed with the KV Cache Compression work as well as the prefix cacheing making queries converge on practically free.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.