Save Money and Prevent Skew: One Container for Sagemaker and Lambda

Product lifecycles often require infrequent machine learning inference. Beta releases, for example, may only receive a small amount of traffic. Hosting model inference in these scenarios can be expensive: model inference servers are always on even if no inference requests are being processed. A good solution to underutilization is serverless offerings such as AWS Lambda. These let you run code on-demand but only pay for the CPU time you use.