Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Sample-level dispatch

Dispatches the next prompt once enough newly completed samples accumulate to meet its assigned GRPO group size, regardless of their originating groups.

source
1
model
1
lab adopt it
1
strongest
default

How sources treat it

One count per evidence span, weakest treatment to strongest.

default 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

Our final approach is sample-level dispatch: once the number of newly completed samples reaches the GRPO group size assigned to the next prompt, we dispatch that prompt regardless of which groups produced those completions.

defaultpost trainingin DeepSeek-V4.1DeepSeek

Filed alongside

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