> This page is for version dev.
> For other versions, use one of these documentation indexes:
> - Latest (v1.5.1) (default): https://docs.nvidia.com/dynamo/latest/llms.txt
> - dev: https://docs.nvidia.com/dynamo/dev/llms.txt
> - v1.5.1: https://docs.nvidia.com/dynamo/v1.5.1/llms.txt
> - v1.5.0: https://docs.nvidia.com/dynamo/v1.5.0/llms.txt
> - v1.4.2: https://docs.nvidia.com/dynamo/v1.4.2/llms.txt
> - v1.4.1: https://docs.nvidia.com/dynamo/v1.4.1/llms.txt
> - v1.4.0: https://docs.nvidia.com/dynamo/v1.4.0/llms.txt
> - v1.3.0: https://docs.nvidia.com/dynamo/v1.3.0/llms.txt
> - v1.2.1: https://docs.nvidia.com/dynamo/v1.2.1/llms.txt
> - v1.2.0: https://docs.nvidia.com/dynamo/v1.2.0/llms.txt
> - v1.1.1: https://docs.nvidia.com/dynamo/v1.1.1/llms.txt
> - v1.1.0: https://docs.nvidia.com/dynamo/v1.1.0/llms.txt
> - v1.0.2: https://docs.nvidia.com/dynamo/v1.0.2/llms.txt
> - v1.0.1: https://docs.nvidia.com/dynamo/v1.0.1/llms.txt
> - v1.0.0: https://docs.nvidia.com/dynamo/v1.0.0/llms.txt
> - v0.9.1: https://docs.nvidia.com/dynamo/v-0-9-1/llms.txt
> - v0.9.0: https://docs.nvidia.com/dynamo/v-0-9-0/llms.txt
> - v0.8.1: https://docs.nvidia.com/dynamo/v-0-8-1/llms.txt
> - v0.8.0: https://docs.nvidia.com/dynamo/v-0-8-0/llms.txt
> - v0.7.1: https://docs.nvidia.com/dynamo/v-0-7-1/llms.txt
> - v0.7.0: https://docs.nvidia.com/dynamo/v-0-7-0/llms.txt

> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt.

# Install

The Dynamo Enterprise Support install path parallels the open-source install path. It uses the same Kubernetes shape, the same values, and the same operational surface. The substantive differences are the container image references and the Helm chart name.

> **Note**
>
> The commands below pin one release. For the release currently in support, use the tags listed in [Supported Artifacts](/dynamo/dev/reference/enterprise/supported-artifacts).

For the full walkthrough of cluster prerequisites, accelerator support, optional multinode orchestration, RDMA, Prometheus, and shared model storage, follow the [Kubernetes Installation Guide](/dynamo/dev/kubernetes/installation/install-dynamo). The steps below cover only what changes for the enterprise images and chart.

## Container Images

The enterprise images are public. Anonymous `docker pull` works from any host with network access to `nvcr.io`. Environments that require authenticated pulls (a bastion registry, an air-gapped mirror, or a policy that blocks anonymous access to `nvcr.io`) can configure an NGC API key on the pulling host; see the [NGC User Guide](https://docs.nvidia.com/ngc/ngc-catalog-user-guide/index.html) for the API-key workflow.

```bash
docker pull nvcr.io/nvidia/ai-dynamo/sglang-runtime-enterprise:1.5.1
docker pull nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime-enterprise:1.5.1
docker pull nvcr.io/nvidia/ai-dynamo/vllm-runtime-enterprise:1.5.1
docker pull nvcr.io/nvidia/ai-dynamo/dynamo-frontend-enterprise:1.5.1
docker pull nvcr.io/nvidia/ai-dynamo/kubernetes-operator-enterprise:1.5.1
```

Kubernetes clusters that already pull from `nvcr.io` need no additional pull secret for the enterprise images. Air-gapped and internal-mirror installs should retag these into the internal registry using the same repository names and versions to keep the manifests portable.

## Platform Helm Chart

The enterprise Helm chart installs the Dynamo Operator. The chart defaults to the open-source Operator repository, so the install command below sets the Operator image to the `-enterprise` repository, which is the supported configuration. etcd, NATS, KAI Scheduler, Grove, and Snapshot ship as bundled subcharts that are all disabled by default; enable the ones a deployment needs, or point the operator at instances you already run. The chart shape, its values, and its Kubernetes surface match the open-source `dynamo-platform` chart. The difference is the chart name.

```bash
export NAMESPACE=dynamo-system
export RELEASE_VERSION=1.5.1

helm fetch https://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/dynamo-platform-enterprise-$RELEASE_VERSION.tgz
helm install dynamo-platform dynamo-platform-enterprise-$RELEASE_VERSION.tgz \
  --namespace $NAMESPACE \
  --create-namespace \
  --set dynamo-operator.controllerManager.manager.image.repository=nvcr.io/nvidia/ai-dynamo/kubernetes-operator-enterprise \
  --set dynamo-operator.controllerManager.manager.image.tag=$RELEASE_VERSION
```

Verify the operator:

```bash
kubectl get crd | grep dynamo
kubectl get pods -n $NAMESPACE
```

The expected CRDs and pods are the same as in the open-source install; see the [Kubernetes Installation Guide](/dynamo/dev/kubernetes/installation/install-dynamo) for the full verification and troubleshooting steps, and for the values that enable the optional subcharts.

## Runtime Images in Deployments

The Dynamo Operator watches `DynamoGraphDeployment` (DGD) resources. Deployments that must run on the enterprise runtime images reference them by their full `-enterprise` image path in the DGD spec. A minimal example:

```yaml
apiVersion: nvidia.com/v1beta1
kind: DynamoGraphDeployment
metadata:
  name: my-agg-deployment
  namespace: dynamo-system
spec:
  components:
    - name: Frontend
      type: frontend
      replicas: 1
      podTemplate:
        spec:
          containers:
            - name: main
              image: nvcr.io/nvidia/ai-dynamo/dynamo-frontend-enterprise:1.5.1
    - name: worker
      type: worker
      replicas: 1
      podTemplate:
        spec:
          containers:
            - name: main
              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime-enterprise:1.5.1
              envFrom:
                - secretRef:
                    name: hf-token-secret
              command:
                - python3
                - -m
                - dynamo.vllm
              args:
                - --model
                - your-org/your-model
```

For the full DGD walkthrough (choosing a model, sizing parallelism, applying and testing the deployment), see [Deploy with DGD](/dynamo/dev/kubernetes/model-deployment/deploy-with-dgd).

## Differences from the Open-Source Install

* **Image references.** Enterprise and open-source images both resolve under `nvcr.io/nvidia/ai-dynamo/`. The enterprise repository names carry an `-enterprise` suffix, which is the only difference.
* **Helm chart.** Enterprise chart: `dynamo-platform-enterprise`. Open-source chart: `dynamo-platform`. The values schema is the same. The enterprise install overrides the Operator repository to the supported `kubernetes-operator-enterprise` image.
* **Support scope.** Only the images and chart listed above are eligible for enterprise support. The Python wheels, Rust crates, and non-listed component containers in the same release remain community-supported.