skills.rest
huggingface
huggingfaceOFFICIAL
Explore all skills by this author →
Website𝕏@huggingfaceGitHub

hf-cloud-sagemaker-production-defaults

Automate SageMaker real-time and async inference endpoint deployment with autoscaling, alarms, and tagging.

10.9k|724|Updated Nov 24, 2025
Search Tags:#deployment#aws#endpoints#cloudwatch#autoscaling#sagemaker
One-click install
npx skills add https://github.com/huggingface/skills --skill hf-cloud-sagemaker-production-defaults
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hf-cloud-sagemaker-production-defaults
Source: https://github.com/huggingface/skills/tree/main/skills/hf-cloud-sagemaker-production-defaults
Command: npx skills add https://github.com/huggingface/skills --skill hf-cloud-sagemaker-production-defaults

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires boto3, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the creation of SageMaker endpoints with production-ready configurations, including autoscaling, CloudWatch alarms, and tagging, streamlining the deployment process and reducing the risk of configuration errors.

Core Features & Use Cases

  • Automated Endpoint Creation: Deploy SageMaker endpoints with pre-configured autoscaling, alarms, and tagging, ensuring a standardized production setup.
  • Real-time and Async Deployments: Supports both real-time and asynchronous inference endpoint configurations.
  • Use Case: When you need to deploy a SageMaker endpoint that will be serving live predictions, this skill helps set up everything needed for a robust deployment with minimal configuration.

Quick Start

Deploy a real-time endpoint with the following command:

python scripts/deploy.py \
    --model-name <model-name> \
    --image-uri <image-uri> \
    --inference-ami-version <ami> \
    --role-arn <role-arn> \
    --instance-type <instance-type> \
    --region <region> \
    --env SM_VLLM_MODEL=<model-id> \
    --env SM_VLLM_HOST=0.0.0.0 \
    --env SM_VLLM_TRUST_REMOTE_CODE=true \
    --env SM_VLLM_MAX_MODEL_LEN=4096

Frequently Asked Questions about hf-cloud-sagemaker-production-defaults

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy a SageMaker endpoint with autoscaling and CloudWatch alarms?▼

You can deploy a SageMaker endpoint with autoscaling and CloudWatch alarms by using an automated script that applies predefined production-ready configurations, including tagging and scaling policies. This streamlines deployment and reduces configuration errors.

What's the best way to automate SageMaker real-time and async inference deployments?▼

Automating SageMaker real-time and async inference deployments is best handled by scripts that pre-configure autoscaling, alarms, and tagging. This ensures a standardized production setup for serving live predictions with minimal manual configuration.

Do I need specific IAM permissions to automate SageMaker endpoint creation?▼

Yes, you need specific AWS SageMaker and related IAM permissions to automate endpoint creation. The deployment script requires these permissions to provision resources, apply autoscaling policies, and configure CloudWatch alarms successfully.

Can I use boto3 to configure SageMaker endpoint autoscaling and tagging?▼

Yes, you can use boto3 to configure SageMaker endpoint autoscaling and tagging. This Skill leverages boto3 scripts to automate the deployment of real-time and asynchronous inference endpoints with predefined production configurations.

What environment variables are needed to deploy a vLLM model on SageMaker?▼

To deploy a vLLM model on SageMaker, you need environment variables like SM_VLLM_MODEL, SM_VLLM_HOST, SM_VLLM_TRUST_REMOTE_CODE, and SM_VLLM_MAX_MODEL_LEN. These are passed to the deployment script to configure the inference endpoint.

Related Skills

Explore More Software Engineering Skills→
huggingfacehuggingface
10.9k

hf-cloud-sagemaker-iam-preflight

Verify or create AWS SageMaker IAM execution roles with AWS CLI.

Official
Advanced
Tyler-R-KendrickTyler-R-Kendrick
1

hf-cloud-sagemaker-production-defaults

Deploy SageMaker endpoints with autoscaling, CloudWatch monitoring, and resource tagging.

Community
Advanced
itsmostafaitsmostafa
1.1k

cloudwatch

Automate AWS CloudWatch monitoring setup for logs, metrics, alarms, and dashboards.

Community
Intermediate
jeremylongshorejeremylongshore
2.6k

generating-infrastructure-as-code

Generate production-ready Infrastructure as Code configurations for Terraform, CloudFormation, Pulumi, ARM, and CDK.

Community
Advanced