Overview

The NVIDIA Dynamo platform is an open-source inference platform with focus on high-performance, low-latency, and scalability. It is designed to serve any AI model agnostically from any inference engine or framework (supports TRT-LLM, vLLM, SGLang or others), architecture or deployment scale.

This appliance is tailored to leverage Dynamo quickstart run feature, enabling a quick way of testing different inference engines and models.

The appliance provides a streamlined solution for building and serving end-to-end AI applications, utilizing pre-trained models from the Hugging Face library.

Download

The latest version of the Dynamo appliance is available for download from the OpenNebula public Marketplace:

• Service Dynamo

Requirements

Minimum requirements vary depending on the selected LLM and its size. We're currently developing hardware recommendations for each available model. However, to ensure optimal performance with even the smallest model, we recommend provisioning a virtual machine with at least 8 GB of RAM and a GPU with a minimum of 14 GB of vRAM.

Release Notes

Detailed release notes for each version are available on the OpenNebula release page, providing comprehensive insights into version-specific updates. The Dynamo appliance is based on Ubuntu 24.04 LTS (x86-64).

Component	Version
Dynamo	0.1.1

---

Next: Dynamo Quick Start