Deploy Triton Inference Server with AWS ECS: Part (3/4)

Author(s): Hao WEI

Originally published on Towards AI.

A step-by-step coding practice

a step-by-step coding practice

pub.towardsai.net

A step-by-step coding practice

pub.towardsai.net

In the last two blogs, we built a triton inference server with preprocess and post process, using an MNIST example. The server was running as a local host. In this blog, we will deploy the server to AWS so that it will be accessible to the public. We will use two aws components: ECR and ECS.

The complete code is publicly available in the following GitHub repository. Before all experiments, it is suggested to create a Python virtual environment, and install all dependencies by pip install -r requirements.txt .

Contribute to haowei-2014/triton development by creating an… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI