Posted On: May 10, 2023
Amazon SageMaker Studio notebooks and Notebook Instances now support ml.p4d and ml.p4de GPU-based instances that provide the best performance for interactive machine learning (ML) workloads in the cloud for applications such as large language models with billions of parameters, natural language processing, object detection and classification, seismic analysis, genomics research, and more. These instances are powered by the latest Intel® Cascade Lake processors and eight NVIDIA A100 Tensor Core GPUs.
ml.p4d instances are available in US East (N. Virginia), US West (Oregon), US East (Ohio), Europe (Ireland), Europe (Frankfurt), Asia Pacific (Tokyo), and Asia Pacific (Seoul) AWS regions for both Studio notebooks as well as Notebook Instances. ml.p4de instances are available in US East (N. Virginia) and US West (Oregon) AWS regions for both Studio notebooks as well as Notebook Instances.
Additionally, SageMaker Notebook Instances now support ml.inf1 instances, which provide high performance and are cost effective. ml.inf1 instances are built from the ground up to support machine learning applications and feature up to 16 AWS Inferentia chips, machine learning chips designed and built by AWS to optimize cost for deep learning inference. To learn more about Inf1 instances, visit the product pages. ml.inf1 instances are available for SageMaker Notebook Instances in multiple AWS regions. Visit the Amazon SageMaker developer guide for more information.