Model techniques map
Techniquespost-trainingrollout & RL infrastructure

implementation detail · filed under post-training

Dialogue prefix matching

Matches an incoming request to an existing dialogue prefix and tokenizes only the new suffix.

Also called Prefix matching.

source
1
models
2
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.

Prefix matching locates the dialogue that an incoming request extends, and only the new suffix is tokenized and passed to the inference engine

usedunclearin MiMo-V2.6 RL and OPD infrastructureXiaomi

Filed alongside

Other methods under post-training :: rollout & RL infrastructure.