Model techniques map
Techniquesinference & servingserving parallelism

implementation detail · filed under inference & serving

Fused reduce-scatter/all-gather collectives

Combines reduce-scatter and all-gather collectives for low-latency communication, built on FlashInfer's Lamport-protocol all-reduce.

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.

low-latency fused reduce-scatter / all-gather collectives built on FlashInfer's Lamport-protocol all-reduce

usedsoftware implementationin vLLM

Filed alongside

Other methods under inference & serving :: serving parallelism.