Practical overview
When it fits
Use it when you want a configurable, self-hosted generative AI stack on Amazon EKS and can provide the AWS and Kubernetes tooling it requires.
Who it is for
- Teams deploying self-hosted LLMs and AI workloads on AWS.
- Kubernetes operators assembling selected inference, gateway, embedding, storage and observability components on EKS.
Documented uses
- Provision infrastructure for a generative AI environment on EKS.
- Select and install AI components and examples through an interactive CLI setup.
- Deploy and manage model-serving or embedding components, including configuring and updating models.
- Assemble an NVIDIA Dynamo inference platform with monitoring, GPU Operator and vLLM components.
Requirements & limits
The repository is public and lists the MIT-0 license.
- The target environment is Amazon EKS; this is infrastructure tooling, not a hosted inference service.
- Setup requires AWS CLI, Terraform, Node.js, kubectl, Helm, Docker and Buildx.
- Interactive setup allows component selection, while demo setup deploys its configured components and examples in order.
- Interactive selections may require additional refresh installs if dependencies are not deployed in order.
- The repository documents a separate ordered installation path for NVIDIA Dynamo.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up a customizable EKS component environment
Use interactive setup to select AI components and examples and have the kit provision infrastructure and install the selections.
Before you start
- AWS CLI
- Terraform
- Node.js
- kubectl
- Helm
Steps
Install project dependencies with npm install.
Run ./cli configure and enter the required environment values.
Run ./cli interactive-setup and select the components and examples to install.
Expected outcome
The kit provisions the required infrastructure using Terraform and installs the selected components and examples.
Guide limitations
- Interactive selections may not be installed in the required order; some components or examples may need refreshing by running the CLI install command again.
Compare options for Model inference and serving
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| GenAI on EKS Starter Kit | Provision infrastructure for a generative AI environment on EKS. | Cloud, Docker, Self-hosted, Server | The repository is public and lists the MIT-0 license. |
| Morphingdb | Import a libtorch model and create predictions from values in a PostgreSQL table. | Docker, Linux, Self-hosted, Server | The README documents a Docker image and a build-from-repository option, followed by connecting to PostgreSQL and enabling the pgdl extension. |
| Gateway — pyadav | Send chat-completion requests to a provider through a common server endpoint. | Server | The repository is public and identifies the project as Apache-2.0 licensed. README installation instructions include binaries, platform package managers and Docker. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 14 October 2026
- Original website title
- aws-samples/sample-genai-on-eks-starter-kit · Official homepage title · retained in its source language

