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
fix security issue of logging llm output (#18980)
Signed-off-by: Lu Fang <fanglu@fb.com> Co-authored-by: Lucia (Lu) Fang <fanglu@meta.com>
Lucia Fang committed
May 31, 2025 at 03:38 UTC
b8b904795d3033c21bcb8f5c36e135e75dc1baf2
1 file changed
+2
-2
vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py
+2
-2
@@ -68,8 +68,8 @@ class Phi4MiniJsonToolParser(ToolParser):
68
len(function_call_arr))
69
except json.JSONDecodeError as e:
70
logger.error(
71
- "Failed to parse function calls from model output: %s. "
72
- "Error: %s", model_output, str(e))
71
+ "Failed to parse function calls from model output. "
72
+ "Error: %s", str(e))
73
74
tool_calls: list[ToolCall] = [
75
ToolCall(