Model techniques map
Techniquesinference & servingKV cache management

general family · filed under inference & serving

Persistent KV-cache management

Manages long-lived global KV storage separately from shorter-lived encoder SWA KV, using bounded replay for missing states.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we separate long-lived global KV storage from short-lived encoder SWA KV in host memory, using bounded replay to approximately reconstruct missing encoder SWA states.

usedinference servingin DeepSeek-V4.1-FlashDeepSeek

Filed alongside

Other methods under inference & serving :: KV cache management.