Manage NIM Deployments#
Use the NeMo Deployment Management service to deploy and manage NIM microservices on your Kubernetes cluster.
The Deployment Management service provides APIs to create, update, and delete NIM deployments and their configurations.
Task Guides#
Perform common deployment management tasks.
Deploy a new NIM instance by specifying the model and configuration via a POST API call.
Retrieve details for a specific NIM deployment, including its status and configuration.
View all NIM deployments in your cluster and their current status.
Modify an existing NIM deployment’s configuration and settings.
Remove a deployed NIM instance using the DELETE API endpoint.
Create a new configuration for NIM deployments with specific resource requirements and settings.
Retrieve details of a specific configuration.
View all available configurations for NIM deployments.
Modify an existing configuration to change resource requirements or settings.
Remove a configuration using the DELETE API endpoint.