Schema.ai· vLLM· Schema 0.2.1
vLLM official site vLLM v0.23.0Log in

max_long_partial_prefills

SchedulerConfig field for the maximum number of prompts longer than long_prefill_token_threshold prefilled concurrently under chunked prefill.

SettingvLLM v0.23.0verified Jul 9

Metric knowledge (0)

No claims about this entity yet.

Availability

max_long_partial_prefills 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:74-78