Model techniques map
Techniquesinference & servingserving parallelism

implementation detail · filed under inference & serving

Round-robin routing for prefill-decode disaggregation

Uses a round-robin vLLM router with prefill-decode disaggregation enabled.

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.

vllm-router --policy round_robin --vllm-pd-disaggregation

usedinference servingin GLM-5.3-FlashZ.ai

Filed alongside

Other methods under inference & serving :: serving parallelism.