From 3cc871aaf1554dfaebce86a6798965ec47e708da Mon Sep 17 00:00:00 2001 From: Guy Stone Date: Tue, 23 Jun 2026 18:46:09 -0400 Subject: [PATCH] [Perf] Skip detokenization in online beam search (#46422) Signed-off-by: Guy Stone Signed-off-by: Guy Stone Co-authored-by: Claude --- vllm/entrypoints/generate/beam_search/online.py | 1 + 1 file changed, 1 insertion(+) diff --git a/vllm/entrypoints/generate/beam_search/online.py b/vllm/entrypoints/generate/beam_search/online.py index 1daef9529be..4d101e9434f 100644 --- a/vllm/entrypoints/generate/beam_search/online.py +++ b/vllm/entrypoints/generate/beam_search/online.py @@ -61,6 +61,7 @@ class BeamSearchOnlineMixin(ABC): logprobs=logprobs_num, max_tokens=1, temperature=temperature, + detokenize=False, ) all_beams = [ BeamSearchSequence(