Gokul Chandra Purnachandra Reddy

Many organizations struggle to migrate VMware workloads due to complex dependencies, network translation challenges, and the need to support both cloud and on-premises targets. In this workshop, you use AWS Transform MGN, an agentic AI service, to execute an end-to-end VMware migration to Amazon EC2 and AWS Outposts.

This session presents a comprehensive approach to deploying small language models (SLMs) to AWS Local Zones and AWS Outposts using Amazon SageMaker and Amazon EKS. We’ll demonstrate how to deliver domain-specific, fine-tuned SLMs from AWS Regions to edge locations for low-latency inference.

Some workloads need to run on premises, at the edge, or in a hybrid scenario due to low latency, data dependencies, data sovereignty, and other regulatory reasons, especially in industries such as manufacturing, healthcare, telecommunications, and financial services.