Amazon SageMaker enables customers to deploy ML models to make predictions (also known as inference) for any use case. You can now deploy large models (up to 500GB) for inference on Amazon SageMaker’s Real-time and Asynchronous Inference options by configuring the maximum EBS volume size and timeout quotas. This launch enables customers to leverage SageMaker’s fully managed Real-time and Asynchronous inference capabilities to deploy and manage large ML models such as variants of GPT and OPT.