Course Outline
Preparing Machine Learning Models for Production
- Packaging models using Docker
- Exporting models from TensorFlow and PyTorch
- Managing versioning and storage requirements
Serving Models on Kubernetes
- An overview of inference server architectures
- Deploying TensorFlow Serving and TorchServe
- Establishing efficient model endpoints
Optimizing Inference Performance
- Implementing effective batching strategies
- Handling concurrent requests efficiently
- Tuning for optimal latency and throughput
Autoscaling ML Workloads
- Utilizing the Horizontal Pod Autoscaler (HPA)
- Leveraging the Vertical Pod Autoscaler (VPA)
- Applying Kubernetes Event-Driven Autoscaling (KEDA)
GPU Provisioning and Resource Management
- Configuring dedicated GPU nodes
- An overview of the NVIDIA device plugin
- Defining resource requests and limits for ML workloads
Model Rollout and Release Management
- Implementing blue/green deployment patterns
- Using canary rollout strategies
- Conducting A/B testing for model evaluation
Monitoring and Observability in Production ML
- Tracking key metrics for inference workloads
- Best practices for logging and tracing
- Creating dashboards and setting up alerting
Security and Reliability Best Practices
- Securing model endpoints against threats
- Implementing network policies and access controls
- Ensuring high availability of services
Summary and Future Directions
Requirements
- A solid grasp of containerized application workflows
- Practical experience with Python-based machine learning models
- Familiarity with core Kubernetes concepts
Target Audience
- ML engineers
- DevOps engineers
- Platform engineering teams
Testimonials (4)
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
How trainer deliver knowledge so effectively
Vu Thoai Le - Reply Polska sp. z o. o.
Course - Certified Kubernetes Administrator (CKA) - exam preparation
The knowledge and exchanges with Augustin
