Course Outline
Getting Machine Learning Models Ready for Deployment
- Packaging models using Docker
- Exporting models from TensorFlow and PyTorch
- Strategies for versioning and storage
Serving Models on Kubernetes
- Introduction to inference servers
- Deploying TensorFlow Serving and TorchServe
- Establishing model endpoints
Optimizing Inference Performance
- Implementing batching strategies
- Managing concurrent request handling
- Tuning latency and throughput
Autoscaling ML Workloads
- Horizontal Pod Autoscaler (HPA)
- Vertical Pod Autoscaler (VPA)
- Kubernetes Event-Driven Autoscaling (KEDA)
Provisioning GPUs and Managing Resources
- Setting up GPU nodes
- Overview of the NVIDIA device plugin
- Defining resource requests and limits for ML workloads
Model Rollout and Release Methodologies
- Blue/green deployments
- Canary rollout patterns
- A/B testing for model assessment
Monitoring and Observability for Production ML
- Metrics for inference workloads
- Best practices for logging and tracing
- Dashboards and alerting systems
Security and Reliability Factors
- Protecting model endpoints
- Network policies and access controls
- Maintaining high availability
Conclusion and Future Steps
Requirements
- Knowledge of containerized application workflows
- Proficiency with Python-based machine learning models
- Basic familiarity with Kubernetes concepts
Target Audience
- ML engineers
- DevOps engineers
- Platform engineering teams
Testimonials (3)
basic understanding of container/kubernetes and how they interact features of the openshift plattform
Eric Scholze - NOW IT GmbH
Course - Introduction to Containers, Kubernetes & OpenShift
About the microservices and how to maintenance kubernetes
Yufri Isnaini Rochmat Maulana - Bank Indonesia
Course - Advanced Platform Engineering: Scaling with Microservices and Kubernetes
The training met expectations with its clear explanations, real-world examples, and hands-on labs that made complex topics easy to understand. It provided valuable insights into container orchestration, security, scaling and many other advanced topics.
