Model techniques map
Techniquesinference & servingKV cache management

ambiguous · filed under inference & serving

Customized heterogeneous KV-cache layout

Uses a customized cache layout, though the evidence does not specify its structure.

Also called customized KV cache layout.

source
1
models
2
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we design a customized KV cache layout.

coreinference servingin DeepSeek-V4DeepSeek

Filed alongside

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