multi model endpoints in sagemaker?

@Tina_Qian - thanks, i went through the documentation, but one thing is not clear to me, are we compressing two trained models into one zipped/tar file?

Actually not. Basically, the SageMaker manages the lifecycle of models hosted on multi-model endpoints in the container's memory. Instead of downloading all of the models from an Amazon S3 bucket to the container when you create the endpoint, SageMaker dynamically loads and caches them when you invoke them. When SageMaker receives an invocation request for a particular model, it first routes the request to an instance behind the endpoint, then downloads the model from the S3 bucket to that instance's storage volume. Finally, it loads the model to the container's memory (CPU or GPU, depending on whether you have CPU or GPU backed instances) on that accelerated compute instance. If the model is already loaded in the container's memory, invocation is faster because SageMaker doesn't need to download and load it.

Maybe the pictures from https://aws.amazon.com/cn/blogs/machine-learning/save-on-inference-costs-by-using-amazon-sagemaker-multi-model-endpoints/ is easy to follow and understand.

Hope it helps.