Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Prompt-level dispatch

Dispatches a new prompt when one GRPO group finishes, a strategy reported to stall on long-tail samples within a group.

Also called prompt-level dispatch of rollout prompts.

source
1
model
1
labs adopt it
0
strongest
not used

How sources treat it

One count per evidence span, weakest treatment to strongest.

not used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we switched to prompt-level dispatch, where a new prompt is dispatched after one GRPO group finishes, but found that it stalled easily on long-tail samples within a GRPO group

not usedpost trainingin DeepSeek-V4.1DeepSeek

Filed alongside

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