Model techniques map
Techniquesinference & servinginference scheduling

specific method · filed under inference & serving

Runtime-signal-based rollout concurrency auto-throttling

A scheduling method that uses runtime load signals to dynamically control the number of requests sent to the inference engine.

Also called auto-throttling mechanism.

source
1
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

We therefore design an auto-throttling mechanism at the LLM request scheduling layer, using runtime signals such as active request count, queued request count, and KV cache utilization to dynamically control how many requests are sent to the inference engine.

coreinference servingin Kimi K3Moonshot AI

Filed alongside

Other methods under inference & serving :: inference scheduling.