diff --git a/python/sglang/srt/multimodal/processors/qwen_vl.py b/python/sglang/srt/multimodal/processors/qwen_vl.py
index 605fbb8d9..7dd36c2dd 100644
--- a/python/sglang/srt/multimodal/processors/qwen_vl.py
+++ b/python/sglang/srt/multimodal/processors/qwen_vl.py
@@ -162,7 +162,7 @@ async def preprocess_video(
     # preprocessed video
     is_video_obj = isinstance(vr, VideoDecoderWrapper)
     if not is_video_obj:
-        return vr
+        return vr, None
     entry_time = time.perf_counter()
 
     total_frames, video_fps = len(vr), vr.avg_fps