NVIDIA NIM Operator

The NVIDIA NIM Operator enables Kubernetes cluster administrators to operate the software components and services necessary to run NVIDIA NIMs in various domains such as reasoning, retrieval, speech, and biology. Additionally, it allows the use of NeMo Microservices to fine-tune, evaluate, or apply guardrails to your models.

The Operator manages the life cycle of the following microservices and the models they use:

NVIDIA NIM models, such as:

• Reasoning LLMs
• Retrieval - Embedding, Reranking, etc.
• Speech
• Biology

NeMo core microservices:

• NeMo Customizer
• NeMo Evaluator
• NeMo Guardrails

NeMo platform component microservices:

• NeMo Data Store
• NeMo Entity Store

A Helm chart is provided for easily deploying the NIM operator in a cluster to provision the NVIDIA NIMs on GPU-enabled nodes.

Government Ready: STIG/FIPS Hardening

This ensures the highest level of security and compliance for regulated environments, the NVIDIA NIM Operator is:

• hardened

Learn more about NVIDIA's hardened image in the AI Software for Regulated Environments White Paper.

Usage

For information on platform support and getting started, visit the official documentation repository

License Agreements

The NVIDIA NIM Operator source code is licensed under Apache 2.0 and contributions are accepted with a DCO. See the contributing document for more information on how to contribute and the release artifacts.

An End User License Agreement is included with this product. By pulling and using the containers from NGC, you accept the terms and conditions of this license.

Suggested Reading

The NIM Operator is open-source. For more information on contributions and release artifacts, see the GitHub repo