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
Fix test named tool use (#27458)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Oct 24, 2025 at 20:27 UTC
41a62564a7b906cbf93862c0e9b35079d828940a
1 file changed
+2
tests/entrypoints/openai/test_completion_with_function_calling.py
+2
@@ -378,6 +378,7 @@ async def test_named_tool_use(
378
messages=messages,
379
max_completion_tokens=1000,
380
tools=tools,
381
+ temperature=0.0,
382
tool_choice=tool_choice,
383
)
384
message = chat_completion.choices[0].message
@@ -399,6 +400,7 @@ async def test_named_tool_use(
400
max_completion_tokens=1000,
401
tools=tools,
402
tool_choice=tool_choice,
403
+ temperature=0.0,
404
stream=True,
405
)
406