fix: update the tags for consistency and remove 0.4.1 refs (#3058)

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

benchmarks/incluster/benchmark_job.yaml

@@ -17,7 +17,7 @@ spec:
         fsGroup: 1000
       containers:
       - name: benchmark-runner
-        image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
+        image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
         securityContext:
           allowPrivilegeEscalation: false
           capabilities:

benchmarks/nixl/nixl-benchmark-deployment.yaml

@@ -18,7 +18,7 @@ spec:
         - name: nvcr-imagepullsecret
       containers:
       - name: nixl-benchmark
-        image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:nixlbench-e42c07a8
+        image: my-registry/vllm-runtime:nixlbench-e42c07a8
         command: ["sh", "-c"]
         args:
           - "nixlbench -etcd_endpoints http://dynamo-platform-etcd:2379 --target_seg_type VRAM --initiator_seg_type VRAM && sleep infinity"

components/backends/sglang/README.md

@@ -130,7 +130,7 @@ uv pip install --prerelease=allow sglang[all]==0.4.9.post6
 <summary>Instructions</summary>
 
 ```bash
-docker pull nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.3.2
+docker pull nvcr.io/nvidia/ai-dynamo/sglang-runtime:my-tag
 ```
 
 </details>

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/sglang/deploy/disagg_planner.yaml

@@ -18,7 +18,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/sglang-runtime:hzhou-0811-1
+          image: my-registry/sglang-runtime:my-tag
     Planner:
       dynamoNamespace: dynamo
       envFromSecret: hf-token-secret
@@ -49,7 +49,7 @@ spec:
         mountPoint: /data
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/sglang-runtime:hzhou-0811-1
+          image: my-registry/sglang-runtime:my-tag
           workingDir: /workspace/components/planner/src/dynamo/planner
           command:
             - /bin/sh
@@ -89,7 +89,7 @@ spec:
         failureThreshold: 10
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/sglang-runtime:hzhou-0811-1
+          image: my-registry/sglang-runtime:my-tag
           workingDir: /workspace/components/backends/sglang
           command:
             - /bin/sh
@@ -106,7 +106,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/sglang-runtime:hzhou-0811-1
+          image: my-registry/sglang-runtime:my-tag
           workingDir: /workspace/components/backends/sglang
           command:
             - python3
@@ -137,7 +137,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/sglang-runtime:hzhou-0811-1
+          image: my-registry/sglang-runtime:my-tag
           workingDir: /workspace/components/backends/sglang
           command:
             - python3

components/backends/trtllm/deploy/README.md

@@ -89,7 +89,7 @@ resources:
 ```yaml
 extraPodSpec:
   mainContainer:
-    image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+    image: my-registry/trtllm-runtime:my-tag
     workingDir: /workspace/components/backends/trtllm
     args:
       - "python3"
@@ -109,7 +109,7 @@ Before using these templates, ensure you have:
 
 ### Container Images
 
-The deployment files currently require access to `nvcr.io/nvidian/nim-llm-dev/trtllm-runtime`. If you don't have access, build and push your own image:
+The deployment files currently require access to `my-registry/trtllm-runtime`. If you don't have access, build and push your own image:
 
 ```bash
 ./container/build.sh --framework tensorrtllm
@@ -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/trtllm/deploy/agg.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
     TRTLLMWorker:
       envFromSecret: hf-token-secret
       dynamoNamespace: trtllm-agg
@@ -24,7 +24,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - /bin/sh

components/backends/trtllm/deploy/agg_router.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
       envs:
         - name: DYN_ROUTER_MODE
           value: kv
@@ -27,7 +27,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - /bin/sh

components/backends/trtllm/deploy/disagg.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
     TRTLLMPrefillWorker:
       dynamoNamespace: trtllm-disagg
       envFromSecret: hf-token-secret
@@ -24,7 +24,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - /bin/sh
@@ -41,7 +41,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - /bin/sh

components/backends/trtllm/deploy/disagg_planner.yaml

@@ -18,7 +18,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/dynamo-dev/dynamo-trtllm-runtime:hzhou-0909-03
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - python3
@@ -69,7 +69,7 @@ spec:
         mountPoint: /data
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/dynamo-dev/dynamo-trtllm-runtime:hzhou-0909-03
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/planner/src/dynamo/planner
           ports:
             - name: metrics
@@ -114,7 +114,7 @@ spec:
         failureThreshold: 10
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/dynamo-dev/dynamo-trtllm-runtime:hzhou-0909-03
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - python3
@@ -152,7 +152,7 @@ spec:
               port: 9090
             periodSeconds: 10
             failureThreshold: 60
-          image: nvcr.io/nvidian/dynamo-dev/dynamo-trtllm-runtime:hzhou-0909-03
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - python3
@@ -186,7 +186,7 @@ spec:
               port: 9090
             periodSeconds: 10
             failureThreshold: 60
-          image: nvcr.io/nvidian/dynamo-dev/dynamo-trtllm-runtime:hzhou-0909-03
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - python3

components/backends/trtllm/deploy/disagg_router.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
       envs:
         - name: DYN_ROUTER_MODE
           value: kv
@@ -27,7 +27,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - /bin/sh
@@ -44,7 +44,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
+          image: my-registry/trtllm-runtime:my-tag
           workingDir: /workspace/components/backends/trtllm
           command:
             - /bin/sh

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
       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

deploy/inference-gateway/helm/dynamo-gaie/values.yaml

@@ -73,7 +73,7 @@ eppAware:
     # Container name for the sidecar
     name: frontend-router
     # Sidecar image
-    image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.4.1
+    image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
     # Image pull policy for the sidecar
     imagePullPolicy: IfNotPresent
     # Command and args for running the frontend in router mode.

docs/_includes/install.rst

@@ -10,7 +10,7 @@ Install a pre-built wheel from PyPI.
    source venv/bin/activate
 
    # Install Dynamo from PyPI (choose one backend extra)
-   uv pip install "ai-dynamo[sglang]==0.4.1"  # or [vllm], [trtllm]
+   uv pip install "ai-dynamo[sglang]==my-tag"  # or [vllm], [trtllm]
 
 
 Pip from source
@@ -41,4 +41,4 @@ Pull and run prebuilt images from NVIDIA NGC (`nvcr.io`).
    docker run --rm -it \
      --gpus all \
      --network host \
-     nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.4.1  # or vllm, tensorrtllm
+     nvcr.io/nvidia/ai-dynamo/sglang-runtime:my-tag  # or vllm, tensorrtllm