Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Predictive Rollout Dispatch

Estimates KV demand and inference concurrency to guide admission and placement of rollouts across ranks.

source
1
models
2
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1core 1

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

We jointly estimate KV demand and expected inference concurrency to guide the admission and placement of new rollouts across ranks.

coreinference servingin MiMo-V2.6Xiaomi

We jointly estimate KV demand and expected inference concurrency to guide the admission and placement of new rollouts across ranks.

usedunclearin MiMo-V2.6 RL and OPD infrastructureXiaomi

Filed alongside

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