For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
LogoLogoCloud Functions
OverviewSelf-ManagedCompute PlaneObservabilityManifestRelease Notes
OverviewSelf-ManagedCompute PlaneObservabilityManifestRelease Notes
    • Overview
    • Quickstart
  • Before You Deploy
    • Infrastructure Sizing
    • Multi-Tenancy
  • Using Cloud Functions
    • API
    • Function Creation
    • LLM Gateway
    • Generic HTTP Function Invocation
    • gRPC Function Invocation
    • Container Functions
    • Helm Functions
    • Streaming Functions
    • Configure Autoscaling
    • CLI
    • Task Creation
    • Container-Based Task Creation
    • Helm-Based Task Creation
  • Load Testing
    • gRPC Load Testing
    • gRPC Load Test SLI Guide
    • HTTP Load Testing
    • HTTP Load Test SLI Guide
    • HTTP Soak Testing
  • Development
    • Architecture Overview
  • Legacy
    • Documentation Archive
    • Function Lifecycle
    • Service Keys
    • Observability
  • Overview
  • Quickstart
  • Infrastructure Sizing
  • Multi-Tenancy
  • API
  • Function Creation
  • LLM Gateway
  • Generic HTTP Function Invocation
  • gRPC Function Invocation
  • Container Functions
  • Helm Functions
  • Streaming Functions
  • Configure Autoscaling
  • CLI
  • Task Creation
  • Container-Based Task Creation
  • Helm-Based Task Creation
  • gRPC Load Testing
  • gRPC Load Test SLI Guide
  • HTTP Load Testing
  • HTTP Load Test SLI Guide
  • HTTP Soak Testing
  • Architecture Overview
  • Local Development
  • Single-cluster (CLI)
  • Single-cluster (Helmfile)
  • Multi-cluster (CLI)
  • Multi-cluster (Helmfile)
  • Documentation Archive
  • NGC-Managed Clusters
  • Helm-Managed Clusters
  • GitOps Cluster Registration
  • Configuration
  • Monitoring
  • Reference
  • Container Cache
  • GXCache
  • KAI Scheduler
  • Function Lifecycle
  • Service Keys
  • Observability
Legacy

Documentation Archive

||View as Markdown|

Earlier documentation uses stack versions. These archives preserve the original guides and their URLs.

DocumentationVersionGuide
Self-Managed Stack1.0.1Installation overview
Compute Plane Stack1.0.0GPU cluster setup
Observability Stack1.0.0Observability
Legacy combined documentation0.6.1Overview
Legacy combined documentation0.6.0Overview
Legacy combined documentation0.5.0Overview
Previous

Multi-cluster (Helmfile)

Next

NGC-Managed Clusters

NVIDIANVIDIA
Developer-friendly docs for your API
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2026, NVIDIA Corporation.