This tutorial describes how to deploy an RTiC server docker image and then how to –
• Run the Deci RTiC Inference Engine (the server).
• Connect the RTiC server to the Deci platform in order to access optimized models.
• Register (launch) the relevant optimized model in the RTiC server in order to enable it to serve
inference requests received from your application (using the Deci RTiC Client).
All these actions are performed using the docker run command and by passing relevant arguments.
Updated 7 months ago