DeepSeek-V4.1-Flash
DeepSeekWe colocate rollout and training on the same physical devices and time-share their execution
specific method · filed under post-training
Runs rollout and training on the same physical devices, time-sharing their execution in the explicitly described implementation.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See rollout & RL infrastructure for the methods filed beside it.
Also called co-located RL training.
2 quotes from 2 sources, one card per model, each opening with its strongest.
We colocate rollout and training on the same physical devices and time-share their execution
We adopt co-located RL training [58] to keep each 1M-context Kimi K3 RL experiment within a few hundred GPUs