From 51906c8c559f1d7c23efa667fcb3b7ed79f7fa25 Mon Sep 17 00:00:00 2001 From: maang-h <55082429+maang-h@users.noreply.github.com> Date: Thu, 27 Nov 2025 18:09:24 +0800 Subject: [PATCH] [Docs] Improve `priority` parameter documentation (#29572) Signed-off-by: maang Signed-off-by: maang-h <55082429+maang-h@users.noreply.github.com> Co-authored-by: Cyrus Leung --- vllm/entrypoints/llm.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/vllm/entrypoints/llm.py b/vllm/entrypoints/llm.py index 1860f383d45fb..f6ee746789981 100644 --- a/vllm/entrypoints/llm.py +++ b/vllm/entrypoints/llm.py @@ -405,6 +405,9 @@ class LLM: lora_request: LoRA request to use for generation, if any. priority: The priority of the requests, if any. Only applicable when priority scheduling policy is enabled. + If provided, must be a list of integers matching the length + of `prompts`, where each priority value corresponds to the prompt + at the same index. Returns: A list of `RequestOutput` objects containing the