From b6fbb9a565a7e27d26e91a064dc83d13b36fa2b6 Mon Sep 17 00:00:00 2001
From: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Date: Sat, 8 Jul 2023 14:48:18 -0700
Subject: [PATCH] Sort the outputs before return (#402)

---
 vllm/entrypoints/llm.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/vllm/entrypoints/llm.py b/vllm/entrypoints/llm.py
index 9c3d3bb454c5..c9ab68525503 100644
--- a/vllm/entrypoints/llm.py
+++ b/vllm/entrypoints/llm.py
@@ -155,4 +155,8 @@ class LLM:
                         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