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] Use 127.0.0.1 instead of localhost in utils (#26750)
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Ye (Charlotte) Qi committed
Oct 14, 2025 at 00:04 UTC
d32c611f455766c9d67034b5e0f8e66f28f4a3ba
1 file changed
+1
-1
tests/utils.py
+1
-1
@@ -157,7 +157,7 @@ class RemoteOpenAIServer:
157
self.host = None
158
self.port = None
159
else:
160
- self.host = str(args.host or "localhost")
160
+ self.host = str(args.host or "127.0.0.1")
161
self.port = int(args.port)
162
163
self.show_hidden_metrics = args.show_hidden_metrics_for_version is not None