Open Models Almanac
Methodsinference & servinginference scheduling

single mention · inference & serving

Sub-NUMA partitioning with NUMA-local worker VMs

Partitions hardware into sub-NUMA domains and binds each worker VM to an individual NUMA domain.

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.

Filed under inference & serving › inference scheduling