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 15, 07:15 UTC
[Bugfix] Consistent ascii handling in tool parsers (#18883)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
May 30, 2025 at 12:44 UTC
77164dad5e7973163d1563f0854644c2864700be
1 file changed
+2
-1
vllm/entrypoints/openai/serving_chat.py
+2
-1
@@ -988,7 +988,8 @@ class OpenAIServingChat(OpenAIServing):
988
tool_calls=[
989
tool_call_class(function=FunctionCall(
990
name=tool_call.name,
991
- arguments=json.dumps(tool_call.parameters)))
991
+ arguments=json.dumps(tool_call.parameters,
992
+ ensure_ascii=False)))
993
for tool_call in tool_calls
994
])
995