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
[CI/Build] fix test function_calling (#25072)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Sep 20, 2025 at 02:16 UTC
47fd08aaf9fe6616d5daf1f30c0377d8b8b7cf21
1 file changed
+1
tests/entrypoints/openai/test_response_api_with_harmony.py
+1
@@ -515,6 +515,7 @@ async def test_function_calling(client: OpenAI, model_name: str):
515
model=model_name,
516
input="What's the weather like in Paris today?",
517
tools=tools,
518
+ temperature=0.0,
519
)
520
assert response is not None
521
assert response.status == "completed"