Open Models Almanac
Methodsinference & servinginference scheduling

single mention · inference & serving

Cross-group cache-hit block pinning

Pins each cache-hit block across groups before allocation to maintain consistency under concurrent scheduling.

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 cross-group pinning of cache-hit blocks.

Filed under inference & serving › inference scheduling