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.
LogoLogoNeMo Platform
  • Documentation
    • Home
    • Get Started
      • Setup
        • Helm
          • Prerequisites
          • Install
          • Database Setup
          • Persistent Volumes
          • File Storage
          • Ingress
          • Multinode Networking
          • OpenShift
          • Backup and Restore
        • Jobs
        • Milvus
        • Observability
        • Security
      • Config Reference
    • Access Control
    • Studio
    • Models and Inference
    • Fine-tune Models
    • Agents
    • Design Synthetic Data
    • Synthesize Safe Data
    • Anonymize Data
    • Guardrail Models
    • Evaluate Models & Agents
    • Vulnerability Scanning
  • Home
  • Get Started
  • Core Concepts
  • Entities
  • Entity References
  • Filtering
  • Manage Files
  • Manage Secrets
  • Projects
  • Workspaces
  • Setup
  • Helm
  • Prerequisites
  • Install
  • Database Setup
  • Persistent Volumes
  • File Storage
  • Ingress
  • Multinode Networking
  • OpenShift
  • Backup and Restore
  • Jobs
  • Milvus
  • Observability
  • Security
  • Helm Reference
  • Config Reference
  • Access Control
  • Overview
  • Concepts
  • Authentication
  • OIDC Setup
  • Using Authentication
  • Providers
  • Azure AD (Entra ID)
  • Generic OIDC
  • Authorization
  • API Scopes
  • Managing Access
  • Permissions Reference
  • Plugin Authorization
  • Policy Engine
  • Roles and Permissions
  • Deployment
  • Configuration
  • Credential Propagation
  • Gateway Integration
  • Production Hardening
  • Security Model
  • Troubleshooting
  • Studio
  • Agents
  • Data Designer
  • Monitor
  • Suggestions
  • Guardrail Configs
  • Virtual Models
  • Models and Inference
  • Tutorials
  • Run Inference
  • Deploy Models
  • Fine-tune Models
  • Customization Concepts
  • Manage Customization Jobs
  • Create a Customization Job
  • Get Job Status
  • List Active Jobs
  • Cancel a Job
  • Training Configuration
  • Customization Job Reference
  • Overview
  • Create a Model Entity
  • Create a Model FileSet
  • Model Catalog
  • Dataset Format
  • Embedding
  • GPT-OSS
  • Llama
  • Llama Nemotron
  • Mistral
  • Phi
  • Qwen
  • Tutorials
  • Understanding Models and Training
  • Format Training Dataset
  • Import HuggingFace Models
  • SFT Customization Job
  • LoRA Customization Job
  • Distillation Customization Job
  • Embedding Customization Job
  • Job Metrics
  • Optimize Throughput
  • Agents
  • Deploy Agents
  • Optimize Agents
  • Secure Agents
  • Plugins and Skills
  • Design Synthetic Data
  • Execution Modes
  • CLI
  • Tutorials
  • The Basics
  • Seeding with External Datasets
  • SDK Resources
  • Migrating from Standalone Library
  • Synthesize Safe Data
  • About
  • Data Synthesis
  • PII Replacement
  • Evaluation
  • Jobs
  • Local and Subprocess Execution
  • Parameters Reference
  • Tutorials
  • Safe Synthesizer 101
  • Differential Privacy
  • SDK Resources
  • Anonymize Data
  • Tutorials
  • Preview a Config
  • Run an Anonymizer Job
  • SDK Resources
  • CLI Reference
  • Guardrail Models
  • Core Concepts
  • Architecture
  • Configurations
  • Configuration Structure
  • Default Configurations
  • Manage Configurations
  • Running Inference
  • Running Checks
  • Tutorials
  • Content Safety
  • Deploy NemoGuard NIMs
  • Injection Detection
  • Multimodal Data
  • Parallel Rails
  • Terminology
  • Observability
  • Evaluate Models & Agents
  • Dataset-Driven vs Task-Driven Evaluation
  • Agent Evaluation
  • Quickstart
  • Evaluate a Deployed Agent over HTTP
  • Evaluate a Harbor Task Suite
  • Score by Component
  • Targets and Runners
  • Writing Metrics
  • Reading Results
  • Tutorials
  • Run LLM-as-a-Judge Evaluation
  • Define and Run Custom Python Metrics
  • SDK Resources
  • Metrics
  • Manage Metrics
  • LLM-as-a-Judge
  • RAG Metrics
  • Similarity Metrics
  • Agentic Metrics
  • Bring Your Own Metric
  • Agent Configuration
  • Model Configuration
  • Vulnerability Scanning
  • Tutorials
  • Run an Audit Locally
  • SDK Resources
  • Configurations
  • Selecting Probes
  • Schema
  • Targets
  • Inference Gateway
  • Schema
  • Release Notes
  • Current Release
  • v0.2.0
  • v0.1.0
  • System Requirements
  • Support Matrix
  • Discover auth configuration
  • Workload identity token exchange JWKS
  • Exchange a workload identity subject token
  • List role bindings
  • Create role binding
  • Get role binding
  • Revoke role binding
  • Get entity by ID (debug/internal)
  • List all workspaces
  • Create a new workspace
  • Get workspace by ID
  • Update workspace
  • Delete workspace
  • List entities
  • Create a new entity
  • Get entity by name
  • Update entity by name
  • Delete entity by name
  • List workspace members
  • Add workspace member
  • Update workspace member roles
  • Remove workspace member
  • List all projects
  • Create a new project
  • Get project by name
  • Update project
  • Delete project
  • List Filesets
  • Create Fileset
  • Get Fileset by Workspace and Name
  • Delete Fileset
  • Update Fileset Metadata
  • Download File Content
  • Upload Fileset Content
  • Delete a specific file from a fileset
  • Get File Metadata
  • List Fileset Files
  • Upload OTLP Logs to Fileset
  • Query OTLP Logs from Fileset
  • Guardrail check request
  • List Guardrail Configs
  • Create Config
  • Get Guardrail Config
  • Delete Config
  • Update Config
  • Model Inference Proxy GET
  • Model Inference Proxy POST
  • Model Inference Proxy PUT
  • Model Inference Proxy DELETE
  • Model Inference Proxy PATCH
  • OpenAI List Models
  • OpenAI Get Model
  • OpenAI Inference Proxy GET
  • OpenAI Inference Proxy POST
  • OpenAI Inference Proxy PUT
  • OpenAI Inference Proxy DELETE
  • OpenAI Inference Proxy PATCH
  • Provider Inference Proxy GET
  • Provider Inference Proxy POST
  • Provider Inference Proxy PUT
  • Provider Inference Proxy DELETE
  • Provider Inference Proxy PATCH
  • Check Provider Readiness
  • List VirtualModels
  • Create VirtualModel
  • Get VirtualModel
  • Delete VirtualModel
  • Update VirtualModel
  • Get Execution Profiles
  • List Jobs
  • Create Job
  • Get Job Result
  • Create Job Result
  • Download Job Result
  • Get Job Step
  • Update Job Step Status
  • List Job Step Tasks
  • Get Job Step Task
  • Update Job Step Task
  • Get Job
  • Delete Job
  • Cancel Job
  • Page Job Logs
  • Pause Job
  • List Job Results
  • Resume Job
  • Get Job Status
  • Update Job Status Details
  • List Steps
  • List Adapters
  • Create Adapter
  • Get Adapter
  • Delete Adapter
  • Update Adapter
  • List ModelDeploymentConfigs By Workspace
  • Create ModelDeploymentConfig
  • Get Specific ModelDeploymentConfig Version
  • Delete Specific ModelDeploymentConfig Version
  • Get Latest ModelDeploymentConfig Version
  • Update ModelDeploymentConfig
  • Delete All ModelDeploymentConfig Versions
  • List ModelDeploymentConfig Versions
  • List ModelDeployments
  • Create ModelDeployment
  • Get Specific ModelDeployment Version
  • Delete Specific ModelDeployment Version
  • Get Latest ModelDeployment
  • Update ModelDeployment
  • Delete All ModelDeployment Versions
  • Get Latest ModelDeployment's Model Entities
  • Update ModelDeployment Status
  • List ModelDeployment Versions
  • List Models
  • Create Model
  • Add Model Adapter
  • Delete Model Adapter
  • Update Adapter
  • Get Model by Workspace and Name
  • Delete Model
  • Update Model
  • List Prompts By Workspace
  • Create Prompt
  • Get Prompt
  • Update Prompt
  • Delete Prompt
  • List ModelProviders By Workspace
  • Create ModelProvider
  • Get ModelProvider
  • Upsert ModelProvider
  • Delete ModelProvider
  • Update ModelProvider Status Fields
  • Admin Rotate Encryption Keys
  • List Secrets
  • Create Secret
  • Get Secret
  • Delete Secret
  • Update Secret
  • Access Secret
  • Python SDK
  • Client APIs
  • CLI Reference
  • Configuration
  • Working with Resources
  • Full CLI Reference
  • Troubleshooting
  • Troubleshooting
  • Customizer
  • Data Designer
  • Evaluator
  • Guardrails
  • Studio
  • Skills Spec
  • EULA
  • Acknowledgements
DocumentationSelf-Managed DeploymentSetup

Install NeMo Platform with Helm

||View as Markdown|

NeMo Platform is bundled in an all-in-one Helm chart for self-managed Kubernetes deployments. Use these guides to deploy the platform on local clusters such as minikube and kind, managed clusters such as EKS, AKS, GKE, and OKE, or on-prem Kubernetes.

Start with Prerequisites, then follow Install. The install guide pins the chart with NMP_HELM_CHART_VERSION and uses the nvidia/nemo-platform NGC org for chart and image access.

Prerequisites

Review the prerequisites for installing the NeMo Platform Helm Chart.

cluster-admin
Install

Install the NeMo Platform using the Helm chart.

cluster-admin on-prem cloud
Database Setup

Set up an external database for the NeMo Platform.

cluster-admin on-prem cloud
Ingress

Set up Ingress for the NeMo Platform.

cluster-admin on-prem cloud
Persistent Volumes

Set up persistent volumes for the NeMo Platform.

cluster-admin on-prem cloud
File Storage

Configure storage options for the Files service.

cluster-admin on-prem cloud
Multinode Networking

Configure high-performance east-west networking (EFA, InfiniBand, TCP-XO, SR-IOV) for multi-node training.

cluster-admin cloud
OpenShift

Install with OpenShift-compatible configuration.

cluster-admin openshift
Backup and Restore

Set up backup and restore configurations for the NeMo Platform.

cluster-admin on-prem cloud
Previous

About Platform Setup

Next

Prerequisites

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.