feat: undo coderabbit requested changes (#1813)

examples/llm/deploy/agg.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -59,7 +59,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -86,7 +86,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo

examples/llm/deploy/agg_router.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -59,7 +59,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -84,7 +84,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -111,7 +111,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo

examples/llm/deploy/disagg.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -59,7 +59,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -86,7 +86,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -113,7 +113,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo

examples/llm/deploy/disagg_router.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -59,7 +59,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -84,7 +84,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -111,7 +111,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo
@@ -138,7 +138,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/llm
           args:
             - dynamo

examples/vllm_v0/deploy/agg.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo
@@ -61,7 +61,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo

examples/vllm_v0/deploy/disagg.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo
@@ -61,7 +61,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo
@@ -88,7 +88,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo

examples/vllm_v0/deploy/disagg_planner.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "4Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo
@@ -62,7 +62,7 @@ spec:
           gpu: "2"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo
@@ -90,7 +90,7 @@ spec:
           gpu: "2"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo
@@ -116,7 +116,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo
@@ -142,7 +142,7 @@ spec:
           memory: "1000Mi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v0
           args:
             - dynamo

examples/vllm_v1/deploy/agg.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -59,7 +59,7 @@ spec:
           memory: "20Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -86,7 +86,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo

examples/vllm_v1/deploy/disagg.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -59,7 +59,7 @@ spec:
           memory: "20Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -86,7 +86,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -113,7 +113,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo

examples/vllm_v1/deploy/disagg_planner.yaml

@@ -34,7 +34,7 @@ spec:
           memory: "4Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -60,7 +60,7 @@ spec:
           memory: "20Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -88,7 +88,7 @@ spec:
           gpu: "2"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -116,7 +116,7 @@ spec:
           gpu: "2"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -142,7 +142,7 @@ spec:
           memory: "2Gi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo
@@ -168,7 +168,7 @@ spec:
           memory: "1000Mi"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:latest
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1
           workingDir: /workspace/examples/vllm_v1
           args:
             - dynamo