Model techniques map
Techniquesinference & servingKV cache management

specific method · filed under inference & serving

Persistent per-dialogue-context KV caching

Keeps a persistent cache per dialogue context so later turns can reuse prior KV and prefill only the new suffix.

Also called Context Caching.

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.

each dialogue context has a persistent key: within one policy version, later turns hit the cached KV—including generated tokens—and prefill only the new suffix.

coreinference servingin MiMo-V2.6Xiaomi

Filed alongside

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