Deploy a machine learning model on SageMaker Serverless Inference for intermittent traffic workloads

Steps

1. Package your model artifacts and push them to an S3 bucket; create a SageMaker Model object referencing the artifact path and the inference container image URI
2. Create an EndpointConfig that includes a ProductionVariant with a ServerlessConfig block, specifying MemorySizeInMB (must be one of the supported values: 1024, 2048, 3072, 4096, 5120, or 6144) and MaxConcurrency
3. Create a SageMaker Endpoint from the EndpointConfig; the endpoint starts in a Creating state and requires no instance type selection
4. Invoke the endpoint using the SageMaker Runtime InvokeEndpoint API with a payload up to 4 MB and a processing timeout of up to 60 seconds
5. Monitor invocation metrics in CloudWatch including invocation count, model latency, and billed duration to understand cost and cold start behavior
6. Set ProvisionedConcurrency in the ServerlessConfig if cold start latency is unacceptable; provisioned concurrency keeps warm instances ready at additional cost