Open Models Almanac
Methodsinference & servingserving parallelism

single mention · inference & serving

Expert parallelism

Distributes MoE experts across ranks to improve throughput.

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

Also called enable expert parallelism.

Filed under inference & serving › serving parallelism