Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Incremental image transfer

Transfers images to the inference engine incrementally and caches CPU-side decoding and preprocessing outputs for reuse.

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.

the reinforcement-learning rollout transfers images to the inference engine only incrementally, and caches the engine’s CPU-side decoding and preprocessing outputs on a distributed file system for reuse

usedunclearin DeepSeek-V4.1-FlashDeepSeek

Filed alongside

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