Skip to main content

Module 6: Model Serving

๐ŸŽฏ Learning Objectivesโ€‹

  • Build REST APIs for ML models with FastAPI
  • Use model serving frameworks (TorchServe, TensorFlow Serving, Triton)
  • Containerize ML models with Docker

๐Ÿ“š Module Contentโ€‹

Chapter 1: REST APIs for MLโ€‹

FastAPI for ML, request/response design, input validation, async endpoints.

Chapter 2: Model Serving Frameworksโ€‹

TorchServe, TensorFlow Serving, Triton Inference Server, BentoML.

Chapter 3: Containerization with Dockerโ€‹

Docker for ML, multi-stage builds, GPU support, image optimization.

๐Ÿš€ Let's Begin!โ€‹

Start with Chapter 1: REST APIs for ML.