[BugFix] Remove incorrect assert in split_decodes_and_prefills (#36553)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-03-09 20:02:02 -07:00
parent 0836be3b03
commit 006aea17d7
1 changed files with 0 additions and 1 deletions
--- 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: