NVIDIA Dynamo Platform is a Kubernetes-native inference platform for serving generative AI and reasoning models at scale. It installs the Dynamo operator with custom resources for graph and component deployments, plus bundled NATS messaging and etcd for a self-contained starting point. Optional Kai Scheduler and Grove integrations can be enabled when clusters need advanced scheduling or multinode orchestration for large model serving workloads.
Manage Dynamo graph, component, checkpoint, model, and scaling resources through Kubernetes-native APIs.
Start with bundled NATS messaging and persistent etcd, then switch to externally managed services when production operations require them.
Enable Kai Scheduler and Grove integrations for advanced scheduling and multinode orchestration.
Expose Dynamo workloads through Kubernetes Ingress or Istio when the cluster has the matching routing layer configured.
Additional Nebius infrastructure costs may apply. Use the Nebius Pricing Page to estimate your infrastructure costs.
Deploy NVIDIA Dynamo Platform on Kubernetes to orchestrate distributed generative AI and reasoning model inference workloads.
Some applications are easier with a hand on the wheel. Talk to an architect who has deployed this in production.
Reliable AI infrastructure backed by top-tier NVIDIA GPUs, purpose-built for demanding inference workloads. Multiple deployment methods — virtual machines for full hardware control, Kubernetes for scalable cluster deployments, and managed serverless applications for teams that want inference running without infrastructure overhead
Learn about Nebius AI CloudNebius meets a broad set of security and compliance standards. Fine-grained IAM controls, audit logs, and encrypted storage are available out of the box — so teams can meet security requirements without additional tooling.
Explore the Trust centerApplication support
Provided by NVIDIA. See the documentation and project links above.
Infrastructure support
Provided by Nebius for the underlying cloud infrastructure.
