Hands-on, interactive lessons for Inference Engineering (Philip Kiely, Baseten Books, 2026). Sibling track: Index of Inference Engineering (reading notes).
Each lesson pairs a short written map with steppable, animated diagrams and a recap quiz.
How to use these Read the matching chapter in the book, then work the diagram step controls top to bottom. Try to predict each step before you advance it.
- Chapter 02 Models
neural networks, LLM mechanics (prefill/decode, attention, MoE), image & video generation, bottlenecks and the roofline, optimizing attention. → [interactive lesson](/inference-engineering-hands-on/chapter-02-models)