Self-hosted NVCF installation includes the core components required for NVCF inference. Additional optional components such as caching and low latency streaming support are also available. Vanity Gateway routing is available only in stack packages that include the Vanity Gateway addon.
For a fresh install, start with the Quickstart. The quickstart uses nvcf-cli self-hosted up to install the control plane, register a GPU cluster, install NVCA, and run basic health checks.
For a full list of required artifacts, see self-hosted-artifact-manifest.
Want to try NVCF locally first? See Local Development to create a k3d cluster, then use the Quickstart local k3d flow.
The control plane and GPU cluster can be the same Kubernetes cluster or separate clusters. The one-click CLI flow supports both layouts.
For remote one-click installs, prepare the Gateway API ingress path and CLI
endpoint configuration before running nvcf-cli self-hosted up. See
Quickstart and Gateway Routing.
Installation steps are as follows:
Mirror NVCF artifacts to your registry. Follow the image mirroring instructions to pull artifacts from NGC and push them to your registry.
Create or select Kubernetes cluster targets. You need a cluster for the control plane and a GPU cluster for function workloads. These can be the same cluster or separate clusters.
Install the self-hosted control plane. Use the Quickstart for a one-click fresh install, Helmfile Installation for manual Helmfile operations, or Standalone Deployment for chart-by-chart installation.
Register a GPU cluster and install the NVIDIA Cluster Agent. The quickstart performs this step. For manual installation paths, see Self-Managed Clusters.
Install Low Latency Streaming if needed for streaming workloads. See LLS Installation.
Install optional enhancements, such as caches, low latency streaming, or Vanity Gateway routing when your stack package includes that addon. See Optional Enhancements.
NVIDIA GPU Operator
Required for GPU workload scheduling. The GPU Operator automates the management of all NVIDIA software components needed to provision GPUs in Kubernetes, including:
See NVIDIA GPU Operator documentation for installation instructions.
Fake GPU Operator for Development/Testing:
For environments without actual GPU hardware, install the fake GPU operator to simulate GPU resources. See fake-gpu-operator for full instructions.
Network Policies
Your cluster must support Kubernetes Network Policies if network isolation is required.
Persistent Storage
A StorageClass must be configured for persistent volumes. Common options:
gp3 (default)local-pathSome cloud providers have minimum PVC size requirements. For example, AWS EBS gp3 volumes have a 1Gi minimum.
See infrastructure-sizing for node pool specifications, storage recommendations, and three recommended sizing tiers (Development, Minimal HA, and Production).
