Course Outline
Preparing Machine Learning Models for Deployment
- Packaging models with Docker for government use
- Exporting models from TensorFlow and PyTorch for government applications
- Versioning and storage considerations for government data management
Model Serving on Kubernetes
- Overview of inference servers for government operations
- Deploying TensorFlow Serving and TorchServe in government environments
- Setting up model endpoints for government services
Inference Optimization Techniques
- Batching strategies for efficient government processing
- Concurrent request handling for government systems
- Latency and throughput tuning for government applications
Autoscaling ML Workloads
- Horizontal Pod Autoscaler (HPA) for government workloads
- Vertical Pod Autoscaler (VPA) for optimizing government resources
- Kubernetes Event-Driven Autoscaling (KEDA) for dynamic government scaling
GPU Provisioning and Resource Management
- Configuring GPU nodes for government operations
- Overview of the NVIDIA device plugin for government use
- Resource requests and limits for ML workloads in government systems
Model Rollout and Release Strategies
- Blue/green deployments for seamless government transitions
- Canary rollout patterns for controlled government releases
- A/B testing for model evaluation in government applications
Monitoring and Observability for ML in Production
- Metrics for inference workloads in government systems
- Logging and tracing practices for government operations
- Dashboards and alerting for government monitoring
Security and Reliability Considerations
- Securing model endpoints for government data protection
- Network policies and access control for government networks
- Ensuring high availability for government services
Summary and Next Steps
Requirements
- An understanding of containerized application workflows for government.
- Experience with Python-based machine learning models for government.
- Familiarity with Kubernetes fundamentals for government.
Audience
- Machine Learning (ML) engineers
- DevOps engineers
- Platform engineering teams
Testimonials (5)
The HPA and VPA
Iulian Popov
Course - Kubernetes Advanced
he was patience and understood that we fall behind
Albertina - REGNOLOGY ROMANIA S.R.L.
Course - Deploying Kubernetes Applications with Helm
The training was more practical
Siphokazi Biyana - Vodacom SA
Course - Kubernetes on AWS
Learning about Kubernetes.
Felix Bautista - SGS GULF LIMITED ROHQ
Course - Kubernetes on Azure (AKS)
It gave a good grounding for Docker and Kubernetes.
