All versions

Claims

1 claim matching "entity.vllm.behavior.chunked_prefill_decode_priority"

Claim	Version	About	Entity	Verified	Sources
The latest optimization docs snapshot says V1 enables chunked prefill by default whenever possible and uses `max_num_batched_tokens` as the token budget for pending prefills.	main-2026-07-21	Behavior	chunked prefill decode-priority scheduling	Aug 20	raw.githubusercontent.com