Serving Image Selection
Independent PiSkill directory guide. The original skill remains hosted by Hugging Face Skills.
What is Serving Image Selection?
Helps choose an appropriate serving container for a Hugging Face model deployment on SageMaker and identify the current container image URI for the target setup.
What does Serving Image Selection do?
Serving Image Selection is a Hugging Face skill for choosing the correct SageMaker inference container family for a Hugging Face model. It distinguishes text-generation LLMs, multimodal models, embeddings, rerankers, diffusion models and other tasks so a deployment uses a compatible and current serving image instead of a guessed container.
Who is Serving Image Selection best for?
- Teams deploying Hugging Face models on SageMaker
- Developers choosing between vLLM, TEI and other inference images
- Projects serving embeddings, rerankers or multimodal models
- Deployment workflows that need a verified container URI before endpoint creation
Common use cases
- Choose a vLLM image for a text-generation model
- Select TEI for embeddings or compatible rerankers
- Choose the right serving family for multimodal or diffusion models
- Resolve a SageMaker container URI before deployment
How does Serving Image Selection work?
The skill inspects the model task and compatibility requirements, maps the workload to the appropriate serving family and resolves the corresponding AWS image. It prioritizes current Hugging Face-curated containers where compatible and documents fallback paths when the preferred image is unavailable.
Key benefits
- Reduces deployment failures caused by incompatible containers
- Covers several model-task families
- Makes model-to-image selection explicit
- Connects directly to later SageMaker deployment workflows
Things to know
- Container recommendations can change as serving stacks evolve
- A compatible image does not guarantee the model fits the target hardware
- Region and version availability can affect the final image choice
Compatible tools
Frequently asked questions
Which container should I use for a Hugging Face LLM on SageMaker?
Is TEI used for every reranker?
Related skills
SageMaker Production Defaults
Guides production-oriented SageMaker endpoint setup with sensible serving modes, autoscaling, monitoring alarms, and tagging instead of a minimal development-only deployment.
AWS Context Discovery
Discovers the active AWS profile, region, account, and caller identity before Hugging Face cloud or SageMaker work so later steps use the correct AWS context.
Python Environment Setup for Hugging Face Cloud
Sets up an isolated Python environment for Hugging Face cloud and SageMaker workflows with an appropriate Python version and current AWS tooling.
Cloud Run Basics
Helps agents deploy and manage Google Cloud Run services, jobs, and worker pools for serverless HTTP apps, scheduled tasks, and background workloads.
AWS CloudFormation
Guides infrastructure-as-code work with AWS CloudFormation, including template authoring, deployment, troubleshooting, stack behavior, dependencies, and production-safe infrastructure changes.
AWS Containers
Guides container workloads on AWS across services such as ECS and ECR, with production-oriented patterns for images, task definitions, deployments, networking, scaling, and troubleshooting.