Build a Triton Inference Server with MNIST Example: Part (1/4)

Author(s): Hao WEI

Originally published on Towards AI.

a step-by-step coding practice

In this series of blogs, we will walk through how to build a triton inference server, host it in AWS ECS, and accelerate the speed using tensorRT. We will use MNIST as an example, which everyone knows. The tech stack includes docker, tensorflow, keras, triton, AWS ECR & ECS, tensorRT, etc. The series is divided into 4 parts.

Part 1/4: we will build a very basic triton server, and use Python to send requests to it.Part 2/4: we will add a preprocess and a postprocess module to the triton server, in order to make the server more versatileA step-by-step coding practice

pub.towardsai.net

Part… 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