Merge branch 'GoogleCloudPlatform:main' into updates

GoogleCloudPlatform · Oct 9, 2024 · da99beb · da99beb
2 parents 728e283 + b0588cc
commit da99beb
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 1 deletion.
diff --git a/benchmarks/inference-server/vllm/manifest-templates/vllm.tftpl b/benchmarks/inference-server/vllm/manifest-templates/vllm.tftpl
@@ -51,6 +51,7 @@ spec:
         - name: vllm
           ports:
             - containerPort: 80
+              name: metrics
           image: "vllm/vllm-openai:v0.5.5"
           command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
           args: ["--model", "${model_id}", "--tensor-parallel-size", "${gpu_count}", "--port", "80", "--swap-space", "${swap_space}", "--disable-log-requests"]

diff --git a/benchmarks/inference-server/vllm/monitoring-templates/vllm-podmonitoring.yaml.tftpl b/benchmarks/inference-server/vllm/monitoring-templates/vllm-podmonitoring.yaml.tftpl
@@ -8,5 +8,5 @@ spec:
     matchLabels:
       app: vllm
   endpoints:
-  - port: 80
+  - port: metrics
     interval: 15s