Model techniques map
Techniquesinference & servingKV cache management

specific method · filed under inference & serving

Stateless in-memory prefix caching

Matches context history in memory to bypass prefill latency without stateful cache management.

Also called stateless prefix caching in memory.

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.

leveraging stateless prefix caching in memory to match context history and instantly bypass prefill latency

usedinference servingin LiteRT-LM serveGoogle

Filed alongside

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