AWS – Amazon SageMaker Inference now supports Multi Model Endpoints for PyTorch

SageMaker Multi-Model Endpoint (MME) is a fully managed capability that allows customers to deploy 1000s of models on a single SageMaker endpoint and reduce costs. Until today, MME was not supported for PyTorch models deployed using TorchServe. Now, customers can use MME to deploy 1000s of PyTorch models using TorchServe to reduce inference costs.

Read More for the details.