AMD Inference Microservice (AIM) - Helm Deployment

In this video, we will walk you through how to deploy an AIM, short for AMD Inference Microservice AIMs are distributed as Docker images, making them easy to deploy and manage in various environments. AIMs provide a mechanism for automatically selecting tailored runtime parameters based on your input, hardware, and model specifications. We will guide you on how to deploy an AIM model on Kubernetes using helm charts.However, you can also deploy using, for example, Docker and KServe. See the documentation for ...