Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Prep Machine Learning Models for Production Deployment
- Model packaging using Docker
- Exporting models from TensorFlow and PyTorch
- Considerations for versioning and storage
Serving Models on Kubernetes
- An overview of inference servers
- Deploying TensorFlow Serving and TorchServe
- Establishing model endpoints
Optimizing Inference Performance
- Strategies for batching requests
- Managing concurrent request handling
- Tuning latency and throughput
Autoscaling ML Workloads
- Horizontal Pod Autoscaler (HPA)
- Vertical Pod Autoscaler (VPA)
- Kubernetes Event-Driven Autoscaling (KEDA)
GPU Provisioning and Resource Administration
- Configuration of GPU nodes
- Overview of the NVIDIA device plugin
- Defining resource requests and limits for ML workloads
Strategies for Model Rollout and Release
- Blue/green deployment patterns
- Canary rollout methodologies
- A/B testing for model assessment
Monitoring and Observability for Production ML
- Key metrics for inference workloads
- Best practices for logging and tracing
- Creating dashboards and setting alerts
Addressing Security and Reliability
- Protecting model endpoints
- Implementing network policies and access controls
- Ensuring high availability
Summary and Future Steps
Requirements
- A solid understanding 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 (1)
I like the Kubernetes part of the training as I had some tasks with K8s pods and ports and it was nice to get a better understanding now. Thank you!