NVIDIA NeMo Microservices
NVIDIA NeMo Microservices
NVIDIA NeMo™ microservices continuously optimize AI agents for peak performance, accelerating and simplifying data flywheels powered by the latest human and AI feedback.
Introduction to NeMo Microservices
Learn about the NeMo microservices, how it works at a high-level, and the key features.
Learn about the NeMo Microservices Platform.
Learn about the key features of the NeMo Microservices Platform.
Release notes for the NeMo microservices.
AI Model Development Workflow
Explore how you can use the NeMo microservices at every stage of your AI workflow.
Iterate on your AI models by managing your projects, datasets, and models.
Fine-tune your models using customization jobs to improve their performance.
Set targets, define configs, and run an evaluation job to measure your model's performance.
Deploy and proxy $NIM for LLMs for inference.
Manage guardrails to moderate user input and model responses.
Tutorial Highlights
Check out tutorials to get a quick start on using the NeMo microservices.
Get started with the end-to-end tutorials for the NeMo microservices.
Learn how to manage the entities like projects, models, and datasets.
Learn how to customize your models using prompts or datasets.
Learn how to evaluate your models.
Learn how to add checks to your model to ensure it behaves as expected.
Deployment Guides
Deploy NeMo Microservices as a platform or individually.
Use the admin setup guide to learn about deploying the NeMo microservices to Kubernetes.
Learn about the different deployment scenarios for setting up the NeMo microservices on Kubernetes.
Deploy all NeMo microservices together as a platform using a single Helm chart.
Deploy any one or more of the NeMo microservices individually.