Model techniques map
Techniquesinference & servingKV cache management

specific method · filed under inference & serving

Request-level prefix cache

Caches request-level prefixes during rollout, including KV cache and routed experts from prior turns.

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 employ a request-level prefix cache during rollout. This cache stores KVCache and MoE routed experts from prior turns

usedinference servingin MiMo-V2-FlashXiaomi

Filed alongside

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