max_num_scheduled_tokens

SchedulerConfig field capping the tokens the scheduler may issue in a single iteration; defaults to max_num_batched_tokens.

SettingvLLM v0.23.0verified Jul 9

No claims about this entity yet.

max_num_scheduled_tokens 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:56-61