[Core] More fixes to MultiModalEmbeddings type handling (#19715)

Signed-off-by: Russell Bryant <rbryant@redhat.com>

vllm/model_executor/models/qwen_vl.py

@@ -754,7 +754,8 @@ class QwenVLForConditionalGeneration(QWenBaseModel, SupportsPP, SupportsLoRA,
     ) -> torch.Tensor:
         inputs_embeds = self.transformer.get_input_embeddings(input_ids)
 
-        if multimodal_embeddings is not None:
+        if multimodal_embeddings is not None \
+            and len(multimodal_embeddings) != 0:
             inputs_embeds = merge_multimodal_embeddings(
                 input_ids, inputs_embeds, multimodal_embeddings,
                 self.transformer.visual.image_pad_id)