fix: update the tags for consistency and remove 0.4.1 refs

Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>

Author: saturley-hall

components/backends/sglang/deploy/README.md

@@ -92,7 +92,7 @@ Edit the template to match your environment:
 
 ```yaml
 # Update image registry and tag
-image: your-registry/sglang-runtime:your-tag
+image: my-registry/sglang-runtime:my-tag
 
 # Configure your model
 args:

components/backends/trtllm/deploy/README.md

@@ -141,7 +141,7 @@ Edit the template to match your environment:
 
 ```yaml
 # Update image registry and tag
-image: your-registry/trtllm-runtime:your-tag
+image: my-registry/trtllm-runtime:my-tag
 
 # Configure your model and deployment settings
 args:

components/backends/trtllm/deploy/agg-with-config.yaml

@@ -34,7 +34,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:my-tag
     TRTLLMWorker:
       envFromSecret: hf-token-secret
       dynamoNamespace: trtllm-agg
@@ -50,7 +50,7 @@ spec:
           configMap:
             name: nvidia-config
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           # mount the configmap as a volume
           volumeMounts:

components/backends/vllm/deploy/README.md

@@ -116,7 +116,7 @@ Edit the template to match your environment:
 
 ```yaml
 # Update image registry and tag
-image: your-registry/vllm-runtime:your-tag
+image: my-registry/vllm-runtime:my-tag
 
 # Configure your model
 args:

components/backends/vllm/deploy/agg.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
     VllmDecodeWorker:
       envFromSecret: hf-token-secret
       dynamoNamespace: vllm-agg
@@ -24,7 +24,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/backends/vllm
           command:
             - /bin/sh

components/backends/vllm/deploy/agg_router.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
       envs:
         - name: DYN_ROUTER_MODE
           value: kv
@@ -27,7 +27,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/backends/vllm
           command:
             - /bin/sh

components/backends/vllm/deploy/disagg.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
     VllmDecodeWorker:
       dynamoNamespace: vllm-disagg
       envFromSecret: hf-token-secret
@@ -24,7 +24,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/backends/vllm
           command:
             - /bin/sh
@@ -41,7 +41,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/backends/vllm
           command:
             - /bin/sh

components/backends/vllm/deploy/disagg_planner.yaml

@@ -20,7 +20,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
     Planner:
       dynamoNamespace: vllm-disagg-planner
       envFromSecret: hf-token-secret
@@ -51,7 +51,7 @@ spec:
         mountPoint: /data/profiling_results
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/planner/src/dynamo/planner
           command:
             - /bin/sh
@@ -91,7 +91,7 @@ spec:
         failureThreshold: 10
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/backends/vllm
           command:
             - /bin/sh
@@ -114,7 +114,7 @@ spec:
               port: 9090
             periodSeconds: 10
             failureThreshold: 60
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/backends/vllm
           command:
             - python3
@@ -139,7 +139,7 @@ spec:
               port: 9090
             periodSeconds: 10
             failureThreshold: 60
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/backends/vllm
           command:
             - python3

components/backends/vllm/deploy/disagg_router.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
       envs:
         - name: DYN_ROUTER_MODE
           value: kv
@@ -27,7 +27,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/backends/vllm
           command:
             - /bin/sh
@@ -44,7 +44,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
           workingDir: /workspace/components/backends/vllm
           command:
             - /bin/sh