Model techniques map
Techniquesinference & servinginference scheduling

specific method · filed under inference & serving

Latency-sensitive execution class with priority isolation

A resource-management method that isolates latency-sensitive tasks through scheduling priority and core scheduling.

Also called a latency-sensitive (LS) execution class.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

DSec therefore introduces a latency-sensitive (LS) execution class. We apply SCHED_IDLE to non-LS tasks to minimize their scheduling priority, and use core scheduling to ensure only tasks of the same priority class execute simultaneously on sibling hyperthreads to eliminate interference.

usedsoftware implementationin DeepSeek Elastic Compute (DSec)DeepSeek

Filed alongside

Other methods under inference & serving :: inference scheduling.