1. Understanding the Open Source AI Stack
4 lessonsMap the components of deployable AI systems from model weights to inference runtimes and hardware.
2. Model Formats and Inference Runtimes
5 lessonsLearn to work with model formats, select inference engines, and understand runtime execution.
3. Quantization and Model Compression
5 lessonsApply quantization techniques to reduce model size and accelerate inference without sacrificing quality.
4. Hardware-Aware Deployment
5 lessonsOptimize inference for CPUs, GPUs, mobile chips, and edge accelerators with hardware-specific techniques.
5. Retrieval-Augmented Generation Systems
5 lessonsBuild systems that combine local models with vector databases and retrieval pipelines for private knowledge access.
6. Edge and Mobile AI Deployment
5 lessonsDeploy models on edge devices and mobile platforms with offline capability and privacy guarantees.
7. Production Operations and System Design
5 lessonsDesign resilient AI systems with monitoring, security, cost control, and upgrade strategies.
Get an email when this course opens