Model techniques map
Techniquesinference & servingKV cache management

specific method · filed under inference & serving

KV-cache-aware placement of one-shot option messages

Appends one-shot option messages after input messages so per-request changes leave history KV cache intact.

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.

One-shot options( tool_choice, response_format) are appended after the input messages, so that per-request changes leave the history KV cache intact.

usedsoftware implementationin Kimi K3Moonshot AI

Filed alongside

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