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.