Deploying a multi-model endpoint
Multi-model endpoints are useful when you're dealing with a large number of models that it wouldn't make sense to deploy to individual endpoints. For example, imagine an SaaS company building a regression model for each one of their 10,000 customers. Surely they wouldn't want to manage (and pay for) 10,000 endpoints!
Understanding multi-model endpoints
A multi-model endpoint can serve CPU-based predictions from an arbitrary number of models stored in S3 (GPUs are not supported at the time of writing). The path of the model artifact to use is passed in each prediction request. Models are loaded and unloaded dynamically, according to usage and to the amount of memory available on the endpoint. Models can also be added to, or removed, from the endpoint by simply copying or deleting artifacts in S3.
In order to serve multiple models, your inference container must implement a specific set of APIs that the endpoint will invoke: LOAD...
