Open Models Almanac
Methodsinference & servinginference kernel

single mention · inference & serving

Expert-optimized Triton kernels

Triton kernels optimized for experts in MoE training; the evidence does not specify the particular optimizations.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See inference kernel for the methods filed beside it.

Filed under inference & serving › inference kernel