# Shipping machine learning to production

Read these guides in order to take a model from a notebook to a monitored, governed production service.

## Stage 1: Packaging and running

1. **[MLOps and AI infrastructure](/topics/mlops-ai-infrastructure)**  
   A practical map of MLOps and AI infrastructure: experiment tracking, model serving, GPUs, Kubernetes, observability, architecture and AI governance.
2. **[Docker](/tools/docker)**  
   Docker packages applications and their dependencies into portable containers that run the same everywhere. Learn images, containers and Dockerfiles.
3. **[Kubernetes](/tools/kubernetes)**  
   Kubernetes runs and manages containers across clusters: scheduling, scaling, self-healing and rolling updates. Learn pods, deployments and its role in AI.

## Stage 2: Tracking and serving

4. **[MLflow](/tools/mlflow)**  
   MLflow is an open-source platform for tracking experiments, packaging and registering models, and tracing and evaluating LLM applications. Learn its components.
5. **[Feature store](/tools/feature-store)**  
   A feature store manages ML features so the same definitions feed training and real-time serving, with point-in-time correctness. Learn how it works.
6. **[NVIDIA Triton Inference Server](/tools/triton)**  
   Triton Inference Server serves models from many frameworks on GPUs and CPUs with dynamic batching, concurrent execution and model ensembles. Learn how it works.
7. **[ONNX Runtime](/tools/onnx-runtime)**  
   ONNX Runtime is Microsoft's cross-platform engine for running ONNX models on CPUs, GPUs and accelerators through pluggable execution providers.

## Stage 3: Operating and governing

8. **[Model monitoring](/tools/model-monitoring)**  
   Model monitoring tracks data drift, prediction drift and performance of deployed models so problems are caught before they cause harm. Learn what to monitor.
9. **[OpenTelemetry](/tools/opentelemetry)**  
   OpenTelemetry is the open standard and toolkit for collecting traces, metrics and logs from applications, vendor-neutral and used for AI systems too.
10. **[Prometheus](/tools/prometheus)**  
   Prometheus is an open-source system for collecting time-series metrics, querying them with PromQL and alerting. Learn scraping, labels, exporters and alerts.
11. **[Model cards](/tools/model-cards)**  
   A model card is a short document describing a model's intended use, data, evaluation, limitations and risks, so users can judge whether it fits their needs.
12. **[AI governance](/tools/ai-governance)**  
   AI governance is the set of policies, roles, processes and controls that make an organisation's AI safe, compliant and accountable. Learn the building blocks.
13. **[EU AI Act](/tools/eu-ai-act)**  
   The EU AI Act regulates AI systems by risk level, with prohibited practices, high-risk obligations, transparency rules and duties for general-purpose AI models.

## How to use this path

Read the steps in order; each guide links onward to related topics, so you can go deeper wherever you need to. If you already know a stage, skip to the next one. All learning paths are listed on [Learning paths](/paths).
