Skip to main content
AmigoFish

NVIDIA Dynamo in 5 Minutes: Dynamo On Kubernetes for AI Inference

From NVIDIA Developer · · 5 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.

If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.

Watch on YouTube

Not rated yet

Description

Your model endpoint works for a demo. What does it take to scale it for your team?

In this episode of Dynamo in 5 Minutes, we walk through deploying NVIDIA Dynamo on Kubernetes, from defining your serving setup to sending requests to a live endpoint.

You’ll learn: • How the Dynamo Operator creates and manages your serving setup • Two deployment paths: describe what you need with DGDR, or customize an existing deployment recipe with DGD • How requests move from an OpenAI-compatible frontend to inference engines such as SGLang, vLLM, or TensorRT-LLM • The full DGDR workflow in a live demo, from deployment spec to a working endpoint

No prior experience with distributed inference required..

➡️ Learn more: https://www.nvidia.com/en-us/ai/dynamo/ 📝 Tech blog: https://developer.nvidia.com/blog/tag/nvidia-dynamo/ 📥 Download: https://github.com/ai-dynamo/dynamo

Chapters: 00:00 Introduction 00:31 Moving beyond a single model server 01:02 How the Dynamo Operator works 01:38 Two deployment paths: DGDR and DGD 02:45 Request flow and architecture 03:59 Demo: From deployment spec to live endpoint 04:52 Wrap-up

Back to NVIDIA Developer · Report a problem