Schema.ai· vLLM
vLLM official site vLLM v0.23.0Sign up

async_scheduling

SchedulerConfig flag controlling async scheduling, which helps avoid gaps in GPU utilization.

SettingvLLM v0.23.0verified Jul 9

Claims (0)

No claims about this entity yet.

Availability

async_scheduling is exposed on SchedulerConfig in the v0.23.0 source snapshot.
vllm.config.scheduler_configcomplete_inventorySchedulerConfig dataclass field surface in vllm/config/scheduler.py

vLLM v0.23.0 config scheduler.py · vllm/config/scheduler.py:146-149