A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[BugFix][easy] Fix flaky test test_gpt_oss_multi_turn_chat (#24549)
Signed-off-by: lacora2017 <yehu@meta.com> Co-authored-by: lacora2017 <yehu@meta.com>
lacora committed
Sep 10, 2025 at 06:14 UTC
0b9a612fa327c4b0f4dedf6dc9b2f8c03eb23e36
1 file changed
+1
-1
tests/entrypoints/openai/test_serving_chat.py
+1
-1
@@ -178,7 +178,7 @@ async def test_gpt_oss_multi_turn_chat(gptoss_client: OpenAI,
178
},
179
{
180
"role": "user",
181
- "content": "What is the weather in Dallas, TX?"
181
+ "content": "What is the weather in Dallas, TX with celsius?"
182
},
183
]
184