#+HashtagPLUS
In

Menu

Post image 1
Post image 2
Post image 3
Post image 4
Post image 5
Post image 6
Post image 7
Post image 8
Post image 9
Post image 10
Post image 11
Post image 12
Post image 13
Post image 14
Post image 15
Post image 16
Post image 17
Post image 18
Post image 19
Post image 20
Post image 21
Post image 22
Post image 23
Post image 24
Post image 25
Post image 26
Post image 27
Post image 28
1 / 28
0

Pushing the Limits of KV Cache Compression · zartbot

Hacker News·Pushing the Limits of KV Cache Compression · zartbot·about 3 hours ago
#9lNFhsUJ
#zartbot#deepseek#kvcache#flash#prefill#article
Reading 0:00
15s threshold

TL;DR When DeepSeek-V4.1 Flash was released, I thought it might just be a post-training iteration version... but after using it for a while, I found it reached nearly 420 Tokens/s in speed, and then Cui said all DeepSeek-V4 Pro models would be taken offline... suddenly I felt this was no small matter... until the Technical Report 《DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression》 [1] was fully released, only then did I realize it should be called DeepSeek-V5 Flash... As the paper title states, the purpose of DeepSeek-V4.1 Flash is to push KVCache compression to the extreme. The main reason is that Long-horizon Agent Workflows cause the Context to grow longer and longer, while various tool calls bring heavy prefill computation pressure. The storage pressure of KVCache in HBM and external SSD is very high, all of which are reasons that make Scaling impossible.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Create free accountLog in
Read More