ml-cloud-deployment
Installation
SKILL.md
ML Cloud Deployment
Overview
Use this skill for deploying ML workloads to managed platforms, Kubernetes, serverless systems, GPU/TPU providers, and lakehouse environments. Start from workload requirements: training or inference, batch or online, latency SLO, throughput, model size, data gravity, compliance, region, hardware, team expertise, and budget.
Platform Selection
| Requirement | Strong choices |
|---|---|
| AWS-native managed lifecycle | SageMaker Studio, Training, Processing, Pipelines, Model Registry, Endpoints, Feature Store, Clarify, Model Monitor |
| GCP-native managed lifecycle | Vertex AI Training, Pipelines, Endpoints, Feature Store, Model Monitoring, AutoML, Matching Engine, TPUs |
| Azure-native managed lifecycle | Azure ML workspaces, compute clusters, pipelines, registries, managed online/batch endpoints, AutoML, Responsible ML |
| Lakehouse/Spark-centric ML | Databricks on AWS/Azure/GCP with MLflow, Delta, Feature Store, Workflows |
| Kubernetes control | EKS/GKE/AKS with Kubeflow, KServe, Seldon, Ray, Triton, custom operators |
| Serverless or fast GPU apps | Modal, Replicate, Cloud Run with GPU where available, Lambda for small CPU inference |
| Flexible GPU rental | Lambda Labs, RunPod, self-managed cloud GPU VMs |
| Ray-native scale-out | Anyscale or Ray clusters on Kubernetes/cloud VMs |