From 3b7c20a6b52f8b9510669131c4ce4d8040099f41 Mon Sep 17 00:00:00 2001 From: Kenichi Maehashi <939877+kmaehashi@users.noreply.github.com> Date: Wed, 1 Oct 2025 23:37:35 +0900 Subject: [PATCH] [Bugfix] Apply same sampling parameters for both `n=1` and `n>1` (#26005) Signed-off-by: Kenichi Maehashi --- vllm/v1/engine/async_llm.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/v1/engine/async_llm.py b/vllm/v1/engine/async_llm.py index 757baecea9ce0..574f8b19c3790 100644 --- a/vllm/v1/engine/async_llm.py +++ b/vllm/v1/engine/async_llm.py @@ -290,7 +290,7 @@ class AsyncLLM(EngineClient): return queue # Fan out child requests (for n>1). - parent_request = ParentRequest(request_id, params) + parent_request = ParentRequest(request_id, request.sampling_params) for idx in range(params.n): request_id, params = parent_request.get_child_info(idx) child_request = request if idx == params.n - 1 else copy(request)