
Plan a model deployment to Amazon SageMaker and pick the right inference pathway
- Open source
- 11.4K GitHub stars
- AI models and LLM tooling


Plan a model deployment to Amazon SageMaker and pick the right inference pathway

Create, inspect, update and delete Agent Platform serving endpoints with gcloud

Sets up and validates NVIDIA physical AI infrastructure for synthetic data workflows

Choose the right SageMaker serving container and current image URI for a model

Deploy Model Garden models to Agent Platform endpoints with cost checks and cleanup

Find or create a least-privilege SageMaker execution role before deploying

Diagnoses and fixes Compute Engine managed instance group autoscaling failures

Guides the agent through a step-by-step Azure OpenAI model deployment with full control

Guides an agent through enabling, tuning and troubleshooting GKE Cluster Autoscaler

Guides an agent through scaling GKE workloads with manual scaling, HPA and VPA

Routes Azure OpenAI model deployments to quick, customized, or capacity-check flows

Diagnoses GKE HPA failures like unknown metrics, FailedGet events and stalled scaling
The closest alternatives to Hf cloud sagemaker production defaults are Hf cloud sagemaker deployment planner, Agent platform endpoint management, Physical AI infrastructure setup and resilient scaling, Hf cloud serving image selection and Agent platform deploy.
Yes. Hf cloud sagemaker deployment planner, Agent platform endpoint management, Physical AI infrastructure setup and resilient scaling have a free or open-source option.