Open Models Almanac
Methodsinference & servingKV cache management

general family · filed under inference & serving

Compressed KV caching

Reduces KV-cache storage requirements through compression, though the evidence does not identify a single compression mechanism.

The sources on this page name it without explaining how it works. The line above is the extraction's one-line gloss. See KV cache management for the methods filed beside it.

Also called Compressed key-value caching, KV cache compression, Smaller KV cache.

sources
3
models
2
lab adopt it
1
strongest
core

Documented in

Evidence

3 quotes from 3 sources, one card per model, each opening with its strongest.

How sources treat it
used 1core 2

DeepSeek-V4.1-Flash

DeepSeekadopted2 sources

Compared with the previous generation, V4.1-Flash's KV cache needs just: 1/4 the HBM, 1/8 the SSD storage

coreinference servingin DeepSeek-V4.1-FlashDeepSeek
1 more from this model

Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation

coreinference servingin DeepSeek-V4.1-FlashDeepSeek
↑