This document is relevant for: Trn2, Trn3

Get started

Set up vLLM Omni Neuron with manual installation or a Neuron DLC, then generate your first video on AWS Trainium.

Setup guide

Choose manual or DLC installation, configure persistent caches, and verify the Neuron environment.

Online serving quickstart

Launch an OpenAI-compatible video server and send your first request.

Offline serving quickstart

Run batch video generation with the offline Omni engine from Python.

This document is relevant for: Trn2, Trn3