docs: Adding redirects

.github/workflows/container-validation-backends.yml

@@ -160,17 +160,14 @@ jobs:
   sglang:
     needs: changed-files
     if: needs.changed-files.outputs.has_code_changes == 'true'
-    # OPS-1140: Uncomment this for sglang arm switch to wideep
-    # strategy:
-    #   fail-fast: false
-    #   matrix:
-    #     platform:
-    #       - { arch: amd64, runner: gpu-l40-amd64 }
-    #       - { arch: arm64, runner: cpu-arm-r8g-4xlarge }
-    # name: sglang (${{ matrix.platform.arch }})
-    # runs-on: ${{ matrix.platform.runner }}
-    # OPS-1140: Remove this runs-on line, replaced with the above line
-    runs-on: gpu-l40-amd64
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - { arch: amd64, runner: gpu-l40-amd64 }
+          - { arch: arm64, runner: cpu-arm-r8g-4xlarge }
+    name: sglang (${{ matrix.platform.arch }})
+    runs-on: ${{ matrix.platform.runner }}
     steps:
       - name: Checkout repository
         uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955  # v4.3.0
@@ -181,9 +178,7 @@ jobs:
         with:
           framework: sglang
           target: runtime
-          platform: 'linux/amd64'
-          # OPS-1140: Replace the above line with the uncommented below line
-          # platform: 'linux/${{ matrix.platform.arch }}'
+          platform: 'linux/${{ matrix.platform.arch }}'
           ngc_ci_access_token: ${{ secrets.NGC_CI_ACCESS_TOKEN }}
           ci_token: ${{ secrets.CI_TOKEN }}
           aws_default_region: ${{ secrets.AWS_DEFAULT_REGION }}
@@ -196,9 +191,7 @@ jobs:
         uses: ./.github/actions/docker-tag-push
         with:
           local_image: ${{ steps.build-image.outputs.image_tag }}
-          push_tag: ai-dynamo/dynamo:${{ github.sha }}-sglang-amd64
-          # OPS-1140: Replace the above line with the uncommented below line
-          # push_tag: ai-dynamo/dynamo:${{ github.sha }}-sglang-${{ matrix.platform.arch }}
+          push_tag: ai-dynamo/dynamo:${{ github.sha }}-sglang-${{ matrix.platform.arch }}
           # OPS-1145: Switch aws_push to true
           aws_push: 'false'
           azure_push: 'true'
@@ -209,8 +202,7 @@ jobs:
           azure_acr_password: ${{ secrets.AZURE_ACR_PASSWORD }}
 
       - name: Run unit tests
-        # OPS-1140: Uncomment the below line
-        # if: ${{ matrix.platform.arch != 'arm64' }}
+        if: ${{ matrix.platform.arch != 'arm64' }}
         uses: ./.github/actions/pytest
         with:
           image_tag: ${{ steps.build-image.outputs.image_tag }}
@@ -219,8 +211,7 @@ jobs:
           test_type: "unit"
           platform_arch: ${{ matrix.platform.arch }}
       - name: Run e2e tests
-        # OPS-1140: Uncomment the below line
-        # if: ${{ matrix.platform.arch != 'arm64' }}
+        if: ${{ matrix.platform.arch != 'arm64' }}
         uses: ./.github/actions/pytest
         with:
           image_tag: ${{ steps.build-image.outputs.image_tag }}

Earthfile

@@ -134,7 +134,7 @@ dynamo-build:
 
 dynamo-base-docker:
     ARG IMAGE=dynamo-base-docker
-    ARG DOCKER_SERVER=my-registry
+    ARG DOCKER_SERVER=nvcr.io/nvidia/ai-dynamo
     ARG IMAGE_TAG=latest
 
     FROM ubuntu:24.04
@@ -175,7 +175,7 @@ all-test:
     BUILD ./deploy/cloud/operator+test
 
 all-docker:
-    ARG DOCKER_SERVER=my-registry
+    ARG DOCKER_SERVER=nvcr.io/nvidia/ai-dynamo
     ARG IMAGE_TAG=latest
     BUILD ./deploy/cloud/operator+docker --DOCKER_SERVER=$DOCKER_SERVER --IMAGE_TAG=$IMAGE_TAG
 
@@ -189,6 +189,6 @@ all:
 
 # For testing
 custom:
-    ARG DOCKER_SERVER=my-registry
+    ARG DOCKER_SERVER=nvcr.io/nvidia/ai-dynamo
     ARG IMAGE_TAG=latest
     BUILD +all-test

benchmarks/incluster/benchmark_job.yaml

@@ -17,7 +17,7 @@ spec:
       containers:
       - name: benchmark-runner
         # TODO: update to latest public image in next release
-        image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
+        image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.6.1
         securityContext:
           allowPrivilegeEscalation: false
           capabilities:

benchmarks/profiler/utils/config.py

@@ -107,7 +107,7 @@ class DgdPlannerServiceConfig(BaseModel):
     volumeMounts: list[VolumeMount] = [VolumeMount()]
     extraPodSpec: PodSpec = PodSpec(
         mainContainer=Container(
-            image="my-registry/dynamo-runtime:my-tag",  # placeholder
+            image="nvcr.io/nvidia/ai-dynamo/dynamo-runtime:0.6.1",  # placeholder
             workingDir=f"{get_workspace_dir()}/components/src/dynamo/planner",
             command=["python3", "-m", "planner_sla"],
             args=[],

components/backends/sglang/deploy/README.md

@@ -61,7 +61,7 @@ resources:
 ```yaml
 extraPodSpec:
   mainContainer:
-    image: my-registry/sglang-runtime:my-tag
+    image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
     workingDir: /workspace/components/backends/sglang
     args:
       - "python3"
@@ -92,7 +92,7 @@ Edit the template to match your environment:
 
 ```yaml
 # Update image registry and tag
-image: my-registry/sglang-runtime:my-tag
+image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
 
 # Configure your model
 args:

components/backends/sglang/deploy/agg.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
     decode:
       envFromSecret: hf-token-secret
       dynamoNamespace: sglang-agg
@@ -24,7 +24,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/backends/sglang
           command:
           - python3

components/backends/sglang/deploy/agg_logging.yaml

@@ -16,7 +16,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
     decode:
       envFromSecret: hf-token-secret
       dynamoNamespace: sglang-agg
@@ -27,7 +27,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/backends/sglang
           command:
           - python3

components/backends/sglang/deploy/agg_router.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
       envs:
         - name: DYN_ROUTER_MODE
           value: kv
@@ -27,7 +27,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/backends/sglang
           command:
           - python3

components/backends/sglang/deploy/disagg-multinode.yaml

@@ -22,7 +22,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
     decode:
       multinode:
         nodeCount: 2
@@ -35,7 +35,7 @@ spec:
           gpu: "4"
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/backends/sglang
           command:
           - python3
@@ -72,7 +72,7 @@ spec:
           gpu: "4"
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/backends/sglang
           command:
           - python3

components/backends/sglang/deploy/disagg.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
     decode:
       envFromSecret: hf-token-secret
       dynamoNamespace: sglang-disagg
@@ -25,7 +25,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/backends/sglang
           command:
           - python3
@@ -61,7 +61,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/backends/sglang
           command:
           - python3

components/backends/sglang/deploy/disagg_planner.yaml

@@ -16,7 +16,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
     Planner:
       dynamoNamespace: dynamo
       envFromSecret: hf-token-secret
@@ -27,7 +27,7 @@ spec:
           mountPoint: /data
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/src/dynamo/planner
           command:
           - python3
@@ -49,7 +49,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/backends/sglang
           command:
             - python3
@@ -85,7 +85,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: my-registry/sglang-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.1
           workingDir: /workspace/components/backends/sglang
           command:
             - python3

components/backends/trtllm/deploy/README.md

@@ -89,7 +89,7 @@ resources:
 ```yaml
 extraPodSpec:
   mainContainer:
-    image: my-registry/trtllm-runtime:my-tag
+    image: nvcr.io/nvidia/ai-dynamo/trtllm-runtime:0.6.1
     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 `my-registry/trtllm-runtime`. If you don't have access, build and push your own image:
+The deployment files currently require access to `nvcr.io/nvidia/ai-dynamo/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: my-registry/trtllm-runtime:my-tag
+image: nvcr.io/nvidia/ai-dynamo/trtllm-runtime:0.6.1
 
 # 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:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.6.1
     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:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.6.1
           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: my-registry/trtllm-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/trtllm-runtime:0.6.1
     TRTLLMWorker:
       envFromSecret: hf-token-secret
       dynamoNamespace: trtllm-agg
@@ -24,7 +24,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: my-registry/trtllm-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/trtllm-runtime:0.6.1
           workingDir: /workspace/
           command:
           - python3

components/backends/trtllm/deploy/agg_router.yaml

@@ -13,7 +13,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: my-registry/trtllm-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/trtllm-runtime:0.6.1
       envs:
         - name: DYN_ROUTER_MODE
           value: kv
@@ -27,7 +27,7 @@ spec:
           gpu: "1"
       extraPodSpec:
         mainContainer:
-          image: my-registry/trtllm-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/trtllm-runtime:0.6.1
           workingDir: /workspace/
           command:
           - python3

components/backends/trtllm/deploy/disagg-multinode.yaml

@@ -95,7 +95,7 @@ spec:
       replicas: 1
       extraPodSpec:
         mainContainer:
-          image: my-registry/trtllm-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/trtllm-runtime:0.6.1
           workingDir: /workspace/components/backends/trtllm
           command:
           - python3
@@ -127,7 +127,7 @@ spec:
             - name: nvidia-config
               mountPath: /workspace/
               readOnly: true
-          image: my-registry/trtllm-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/trtllm-runtime:0.6.1
           workingDir: /workspace/
           command:
           - python3
@@ -167,7 +167,7 @@ spec:
             - name: nvidia-config
               mountPath: /workspace/
               readOnly: true
-          image: my-registry/trtllm-runtime:my-tag
+          image: nvcr.io/nvidia/ai-dynamo/trtllm-runtime:0.6.1
           workingDir: /workspace/
           command:
           - python3