Open Models Almanac
Methodsinference & servinginference scheduling

single mention · inference & serving

Caching invariant action-expert intermediates

Reuses context-dependent and position-dependent action-expert intermediates across flow steps.

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

Also called cache reusable action-expert intermediates.

Filed under inference & serving › inference scheduling