Model techniques map
Techniquesinference & servinginference kernel

implementation detail · filed under inference & serving

Triton MoE kernel

A MoE kernel implemented in Triton, identified as a fallback in the evidence.

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.

fall back to the Triton MoE kernel

usedinference servingin vLLM

Filed alongside

Other methods under inference & serving :: inference kernel.