Production AI Systems: sections and modules
T4.8Partly ready
Model adaptation and inference serving
Choose prompting, RAG or fine-tuning; size serving.
About 5 h 3 min: 18 min reading + 4 h 45 min practice · 4 lessons
- Scope
- Adaptation and serving; optional for the FDE path
- Prerequisites
Lessons
Start module- 1Four Learning Surfaces
5 min · Credited source
- 2The Skill Library and Its Promotion Gate
4 min · Credited source
- 3When Fine-Tuning Earns Its Cost
5 min · Credited source
- 4The Data Flywheel
4 min · Credited source
Also used in this module
Lessons taught in another module that this one builds on.
- Model Development and Post-Training
45 min · Opens the practice page
- LLM Inference Serving
48 min · Opens the practice page
Practise and Check
- Deliverable
- Serving sizing exercise
- Assessment
- Checkpoint
- Interview probe
- Fine-tune or RAG? How many GPUs?
- Common mistakes
- Fine-tuning to inject facts
Your Progress
Saved in this browser when you leave the box.