Update quadlet and fleet image tags to 425da63

github-actions[bot] · github-actions[bot] · commit da9f22da4b93 · 2026-03-25T15:45:19.000Z
diff --git a/scenarios/quadlet/vllm-bench.container b/scenarios/quadlet/vllm-bench.container
@@ -3,7 +3,7 @@ Description=vLLM Benchmark Load Generator
 After=vllm-server.service
 
 [Container]
-Image=quay.io/redhat-et/vllm-server:v1.0.202603251001
+Image=quay.io/redhat-et/vllm-server:425da63
 Volume=model-storage.volume:/models:ro,z
 Network=mlops.network
 Entrypoint=["bash", "-c", "until curl -sf http://vllm-server:8000/health; do sleep 10; done && vllm bench serve --base-url http://vllm-server:8000 --model Llama-3.2-1B-Instruct --tokenizer /models --request-rate 5.0 --num-prompts 500"]
diff --git a/scenarios/quadlet/vllm-server.container b/scenarios/quadlet/vllm-server.container
@@ -3,7 +3,7 @@ Description=vLLM GPU Inference Server
 After=network-online.target model-car.service
 
 [Container]
-Image=quay.io/redhat-et/vllm-server:v1.0.202603251001
+Image=quay.io/redhat-et/vllm-server:425da63
 Volume=model-storage.volume:/models:ro,z
 PublishPort=8000:8000
 AddDevice=nvidia.com/gpu=all
diff --git a/scenarios/scenario-01-device-edge/flightctl/fleet.yaml b/scenarios/scenario-01-device-edge/flightctl/fleet.yaml
@@ -14,7 +14,7 @@ spec:
       applications:
         - name: mlops-gpu-stack
           appType: quadlet
-          image: quay.io/redhat-et/mlops-quadlet:v1.0.202603251512
+          image: quay.io/redhat-et/mlops-quadlet:425da63
       config:
       - name: inference-server-metrics
         gitRef: 
