Christian Kamwangala

Go from dataset to a custom foundation model in a few hours, without the need to set up any infrastructure. In this hands-on workshop, you will fine-tune LLMs using Amazon SageMaker Serverless Model Customization, requiring no infrastructure.

Master Large Language Model (LLM) inference optimization on Amazon SageMaker through real-world architectural patterns. This technical session shows ML engineers and architects how to optimize performance and costs using quantization, batching strategies, and GPU/Inferentia hardware selection.