Model Serving Systems: Containers, APIs & Scalability

О курсе

"Docker and Model Serving: Deploy ML APIs with FastAPI and ONNX is designed for ML engineers, MLOps practitioners, and backend developers who want to take models from notebooks to production. You'll learn to build Docker containers for ML workloads, design scalable REST APIs with FastAPI, serialize models with ONNX and SavedModel, and deploy with zero-downtime strategies like blue-green and canary releases. The first module covers Docker fundamentals, image optimization, multi-stage builds, secrets management, and Docker Compose for multi-container ML apps. The second module focuses on REST API design with FastAPI, model versioning, input validation with Pydantic, structured logging, and production-grade error handling. The third module teaches scaling strategies — horizontal scaling, async queues, load balancing, batch vs. real-time inference, and latency optimization for high-throughput serving. The final module covers model serialization formats (ONNX, pickle, SavedModel), blue-green and canary deployments, automated rollback, and disaster recovery. By the end of this course, you will: - Build and optimize Docker images for ML models using multi-stage builds and Compose - Design scalable FastAPI endpoints with versioning, validation, and observability - Scale ML inference with async queues, load balancing, and latency optimization - Deploy models with ONNX serialization and zero-downtime blue-green rollbacks"

Навыки, которые вы освоите

Учитесь у экспертов

Board Infinity

Instructor