[Bugfix] Fix handling of image embeds in models (#29480)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/model_executor/models/llava_next.py

@@ -460,7 +460,7 @@ class LlavaNextForConditionalGeneration(nn.Module, SupportsMultiModal, SupportsP
         image_input: LlavaNextImageInputs,
     ) -> torch.Tensor | list[torch.Tensor]:
         if image_input["type"] == "image_embeds":
-            return [image_input["data"]]
+            return image_input["data"]
 
         patch_embeddings = self._process_image_pixels(image_input)