diff --git a/swift/llm/deploy.py b/swift/llm/deploy.py
index 89182ec25d..1359f59485 100644
--- a/swift/llm/deploy.py
+++ b/swift/llm/deploy.py
@@ -189,8 +189,7 @@ async def _prepare_request(request: Union[ChatCompletionRequest, CompletionReque
                 f'the model `{model_or_engine.model_type}` is in text generation format. '
                 'Please use the `completions` API.')
         messages = request.messages
-        if _args.is_multimodal:
-            compat_openai(messages, request)
+        compat_openai(messages, request)
         # For agent, check if response is endwith observations and join tool observation
         messages_join_observation(messages)
         example = messages_to_history(messages)
diff --git a/swift/llm/utils/template.py b/swift/llm/utils/template.py
index 2aabadd77d..eb5d555943 100644
--- a/swift/llm/utils/template.py
+++ b/swift/llm/utils/template.py
@@ -3379,19 +3379,20 @@ def data_collator(self, batch: List[Dict[str, Any]], padding_to: Optional[int] =
         media_offset = []
         cusum_offset = 0
 
-        
-        for bi,b in enumerate(batch):
+        for bi, b in enumerate(batch):
             if 'media_offset' in b:
                 max_sequence_length = res['input_ids'].shape[1]
                 curr_media_offset = b['media_offset']
-                if curr_media_offset.shape[1]<max_sequence_length:
-                    padding = curr_media_offset[:,-1:,:].expand(curr_media_offset.shape[0], max_sequence_length-curr_media_offset.shape[1], curr_media_offset.shape[2])
+                if curr_media_offset.shape[1] < max_sequence_length:
+                    padding = curr_media_offset[:, -1:, :].expand(curr_media_offset.shape[0],
+                                                                  max_sequence_length - curr_media_offset.shape[1],
+                                                                  curr_media_offset.shape[2])
                     curr_media_offset = torch.concat([curr_media_offset, padding], dim=1)
                 media_offset.append(curr_media_offset + cusum_offset)
                 cusum_offset += num_images[bi]
 
         # media_offset = [b['media_offset'] for b in batch if 'media_offset' in b]
-        
+
         if media_offset:
             res['media_offset'] = torch.concat(media_offset)
         return res