Model techniques map
Techniquesinference & servinginference kernel

implementation detail · filed under inference & serving

Separate-stream shared-expert GEMM overlap

Dispatches shared-expert GEMMs to a separate stream so they overlap with other kernels.

Also called separate stream.

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.

For the shared experts, we dispatch their GEMMs to a separate stream so that they overlap with other kernels.

coresoftware implementationin Kimi K3Moonshot AI

Filed alongside

Other methods under inference & serving :: inference kernel.