Model techniques map
Techniquesinference & servingKV cache management

specific method · filed under inference & serving

Dynamic allocation of fixed-size state-cache pools

Preallocates a limited pool of fixed-size state caches and dynamically assigns them to sequences.

source
1
models
2
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 pre-allocate a fixed- and limited-size pool of state caches, and dynamically assign it to each sequence.

usedinference servingin DeepSeek-V4DeepSeek

Filed alongside

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