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, 01:00 UTC
[CI/CD][bugfix]fix: error argument to loads has incompatible type (#21223)
Signed-off-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com> Signed-off-by: Sungjae Lee <sung-jae.lee@navercorp.com>
Sungjae Lee committed
Jul 19, 2025 at 21:16 UTC
da6579bf41754e442de8f0a3ffa9652e02613618
1 file changed
+2
-2
vllm/engine/arg_utils.py
+2
-2
@@ -1266,8 +1266,8 @@ class EngineArgs:
1266
)
1267
1268
observability_config = ObservabilityConfig(
1269
- show_hidden_metrics_for_version=self.
1270
- show_hidden_metrics_for_version,
1269
+ show_hidden_metrics_for_version=(
1270
+ self.show_hidden_metrics_for_version),
1271
otlp_traces_endpoint=self.otlp_traces_endpoint,
1272
collect_detailed_traces=self.collect_detailed_traces,
1273
)