Open Models Almanac
Methodsinference & servingserving parallelism

single mention · inference & serving

Tensor and expert parallelism

Combines tensor parallelism with expert parallelism to distribute inference across GPUs.

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.

Filed under inference & serving › serving parallelism