Guides

Task-oriented walkthroughs for common AIM Engine workflows.

• Deploying Services — Deploy and manage inference endpoints

• Model Catalog — Browse and select models

• Scaling and Autoscaling — Replicas, KEDA, and metrics

• Model Caching — Pre-cache models for faster startup

• Routing and Ingress — Gateway API patterns and path templates

• Private Registries — Authentication for Hugging Face, S3, and OCI

• Multi-Tenancy — Namespace isolation patterns