hf-cloud-sagemaker-production-defaults
Deploy SageMaker endpoints that scale with traffic.
What it does
Deploys SageMaker inference endpoints with autoscaling, monitoring alarms, and consistent resource tags.
When to use it
Use when creating a SageMaker endpoint, writing create_endpoint deployment code, or finalizing a deployment after selecting its image and execution role.
How to use it
Give it the resolved model deployment settings; it creates the endpoint and associated AWS resources, checks inference, and returns deployment details.
Uses
Good to know
- cannot be undone: SageMaker
What you need · 8
Requires Python to run the bundled deployment scripts.
The deployment scripts import boto3 to call AWS services.
Access · 5
This skill
SageMaker
Starts billable SageMaker endpoints (irreversible)
Creates SageMaker deployment resources
Sends inference test payloads
Application Auto Scaling
Configures automatic endpoint scaling