Overview

The Dynamo Kubernetes Operator simplifies the deployment, configuration, and lifecycle management of Dynamo inference graphs in Kubernetes environments. It automates the reconciliation of custom resources (CRDs) to ensure your desired state is always achieved, managing health checks, scaling, and component coordination directly through Kubernetes primitives. CRDs are embedded in the operator image and applied automatically via an init container.

kubernetes-operator-enterprise is part of the NVIDIA Dynamo Enterprise collection. It is published separately from the open-source release; the -enterprise suffix marks what NVIDIA supports commercially. At the same version, kubernetes-operator-enterprise:<version> contains the same binaries as kubernetes-operator:<version>.

Quick Links: Key Components | Access and Support | Release Info | Getting Started | Support

Key Components

• DynamoGraphDeployment (DGD): Canonical live deployment for a Dynamo inference graph. Defines the complete topology including frontend, router, planner, and worker configurations.
• DynamoGraphDeploymentRequest (DGDR): Deploy-by-intent request. Profiles a model and hardware target and generates a DGD.
• DynamoComponentDeployment (DCD): Per-component deployment (frontend, router, prefill, decode, planner). Created by the operator from a DGD.
• DynamoGraphDeploymentScalingAdapter: Scaling interface used by Planner or external autoscalers to adjust component replicas for SLA-aware autoscaling based on real-time load and latency metrics.
• Additional CRDs: DynamoModel, DynamoCheckpoint, DynamoWorkerMetadata, PodSnapshot, and PodSnapshotContent cover model lifecycle, checkpoint and restore, service discovery, and pod snapshots. Nine CRDs ship with the operator at 1.4.1. PodSnapshot and PodSnapshotContent are owned by ai-dynamo/snapshot; the operator consumes them and does not reconcile them.
• Validation Webhooks: Validates CRD configurations at submission time, preventing invalid deployments before they start.
• Kubernetes-Native Service Discovery: Uses EndpointSlices for service discovery, eliminating etcd dependency in Kubernetes deployments.

For more information, see the Dynamo Operator guide and Install the Dynamo Platform.

Access and Support

• Access and use: Available without an NVIDIA AI Enterprise subscription and at no charge for access and use in development or production.
• Commercial support: An active NVIDIA AI Enterprise subscription is required to open commercial support cases and receive NVIDIA Enterprise Support.
• Scope: Only the exact -enterprise artifacts and versions listed in the Dynamo Enterprise collection are covered. An artifact being identical to a supported one does not put it in support scope. Recipes are not in scope.

See Dynamo Enterprise for scope, supported artifacts, and coverage terms.

Release Info

For the complete release history including architecture details, see the Release Artifacts page. Pre-built containers are available for both x86_64 (AMD64) and ARM64 architectures.

Getting Started

1. Select the Tags tab and locate the container image release that you want to run.
2. In the Pull Tag column, click the icon to copy the docker pull command.
3. Open a command prompt and paste the pull command. Ensure the pull completes successfully.
4. Install using Helm (recommended). CRDs are applied by the operator; do not install dynamo-crds.

export RELEASE_VERSION=<version>
ngc registry chart pull nvidia/ai-dynamo/dynamo-platform-enterprise:$RELEASE_VERSION
helm install dynamo-platform dynamo-platform-enterprise-$RELEASE_VERSION.tgz \
  --namespace dynamo-system \
  --create-namespace

For next steps, including Grove, KAI Scheduler, and Prometheus options, see Install the Dynamo Platform.

Support Matrix

Please refer to the Compatibility page for detailed hardware, architecture, and Kubernetes version support.

Related Containers

• vLLM Runtime - vLLM inference backend
• SGLang Runtime - SGLang inference backend
• TensorRT-LLM Runtime - TensorRT-LLM inference backend
• Dynamo Frontend - Standalone frontend

Security Vulnerabilities in Open Source Packages

Please review the Security Scanning tab to view the latest security scan results.

For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.

License

NVIDIA Dynamo is released under the Apache-2.0 open-source license, making it freely available for development, research, and deployment.

Enterprise Support

An active NVIDIA AI Enterprise subscription adds the support channel. Security patches ship in the releases themselves, in the same artifacts for all users.

• Security Patching: NVIDIA prioritizes patching vulnerabilities categorized as Critical and High severity, based on CVSS and NVIDIA's scanning logic, and ships fixes roll-forward in subsequent Dynamo releases. Medium and Low severity findings are addressed best-effort.
• Bug Intake: Subscribers file issues through NVIDIA Enterprise Support. Fixes land on main and ship roll-forward in the next Dynamo release; there is no on-demand or backport release for bugs.
• Release Coverage: Support covers Dynamo major and minor releases, and the patch releases (1.X.1) that ship security fixes between them.
• Hardware Scope: Support covers the hardware, operating systems, and architectures listed in the published Compatibility matrix and is not scoped to individual models.

Get Help

• NVIDIA AI Enterprise customers: File a support case through NVIDIA Enterprise Support.
• Community and out-of-scope questions: Refer to the Dynamo Documentation or file on Dynamo GitHub Issues.
• Release Notes: GitHub Releases