Announcing Regional Expansion of ml.p4d instances on SageMaker Inference

We are pleased to announce the general availability of ml.p4d instances, in Asia Pacific (Tokyo) and Europe (Frankfurt), to deploy machine learning (ML) models for Real-time and Asynchronous inference on Amazon SageMaker.

ml.p4d.24xlarge instances deliver high performance for deep learning models. With 40 GB of memory per Nvidia A100 GPU, P4d instances enable high performance machine learning inference on large models and generative AI in applications such as natural language processing, object detection and recommendation engines.

Users can start deploying models for inference to ml.p4d instances in Asia Pacific (Tokyo) and Europe (Frankfurt) on SageMaker immediately. For pricing information on this instance, please visit our pricing page. For more information on deploying models with SageMaker, see the overview here and the documentation here. To learn more about the p4d instances see the P4 product page.