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 11, 06:15 UTC
[Bugfix] Fix Unicode issues in GLM-4 tool calling (#30920)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Dec 18, 2025 at 15:12 UTC
aa7e8360559e639f201f08a4deee490af332b22c
1 file changed
+2
-1
vllm/tool_parsers/glm4_moe_tool_parser.py
+2
-1
@@ -114,7 +114,8 @@ class Glm4MoeModelToolParser(ToolParser):
114
ToolCall(
115
type="function",
116
function=FunctionCall(
117
- name=tc_name, arguments=json.dumps(arg_dct)
117
+ name=tc_name,
118
+ arguments=json.dumps(arg_dct, ensure_ascii=False),
119
),
120
)
121
)