From 006aea17d7de338ab9f9e13bfe566715782d19a4 Mon Sep 17 00:00:00 2001 From: Woosuk Kwon Date: Mon, 9 Mar 2026 20:02:02 -0700 Subject: [PATCH] [BugFix] Remove incorrect assert in split_decodes_and_prefills (#36553) Signed-off-by: Woosuk Kwon --- vllm/v1/attention/backends/utils.py | 1 - 1 file changed, 1 deletion(-) diff --git a/vllm/v1/attention/backends/utils.py b/vllm/v1/attention/backends/utils.py index 1b030eaf14..42459815ef 100644 --- a/vllm/v1/attention/backends/utils.py +++ b/vllm/v1/attention/backends/utils.py @@ -528,7 +528,6 @@ def split_decodes_and_prefills( # requests may have a query length of 0 but since they are padding its fine # to treat them as decodes (ensures num_decodes matches the captured size) if torch.all((query_lens == query_lens[0]) | (query_lens == 0)): - assert num_reqs * query_lens[0] == num_tokens, "tokens not padded correctly" return num_reqs, 0, num_tokens, 0 # all decodes is_prefill = query_lens != query_lens[0] else: