Sort the outputs before return (#402)

Author: WoosukKwon

vllm/entrypoints/llm.py

@@ -155,4 +155,8 @@ def _run_engine(self, use_tqdm: bool) -> List[RequestOutput]:
                         pbar.update(1)
         if use_tqdm:
             pbar.close()
+        # Sort the outputs by request ID.
+        # This is necessary because some requests may be finished earlier than
+        # its previous requests.
+        outputs = sorted(outputs, key=lambda x: int(x.request_id))
         return outputs