Open Models Almanac
Methodsinference & servinginference scheduling

single mention · inference & serving

Prefix-cache-aware session affinity scheduling

Routes a session to a cluster holding its prefix cache while limiting the cost of cluster failures.

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-aware affinity scheduling.

Filed under inference & serving › inference scheduling