Machine Learning Model Optimization

Get an introduction to key concepts and goals of model optimization in this course overview with a welcome video.

Explore model optimization, key metrics like latency, throughput, memory footprint, and perplexity, with hands-on demos, exercises, and quizzes for practical understanding.

Explore quantization to shrink models, speed up inference, and lower costs by converting weights/activations to lower precision, using PTQ, QAT, and popular tools like Hugging Face Optimum.

Learn how pruning removes unnecessary neural network weights for smaller, faster, energy-efficient models, covering unstructured and structured methods, tools, and quantization synergy.

Learn to analyze and optimize ML model performance using profiling tools like PyTorch Profiler and TensorBoard to find bottlenecks, tune data pipelines, and validate improvements.

Explore model compression's importance, major techniques, tools, and real-world applications to make AI models smaller, faster, and efficient for deployment on diverse devices.

Learn methods to compress trained models—quantization, pruning, and graph optimizations—for efficient deployment without retraining or original training data.

Learn how training-time compression techniques like quantization-aware training, pruning, distillation, and NAS create efficient AI models by embedding optimization directly into training.

Discover how to design multi-stage, collaborative model compression pipelines by combining and sequencing techniques to maximize efficiency for cloud, mobile, and edge deployments.

Explore efficient AI model architectures, hardware optimization, profiling tools, and hands-on exercises for selecting hardware and debugging performance bottlenecks.

Learn to design, optimize, and deploy efficient neural networks for mobile and edge platforms, considering hardware constraints and using hands-on modern techniques for model efficiency.

Explore tools and libraries for hardware acceleration across GPU, mobile, and edge, optimizing inference with TensorRT, LiteRT, OpenVINO, and ONNX Runtime.

Explore how efficient AI architectures and hardware acceleration combine for production, with real-world cases and hands-on GPU and cross-platform optimization exercises.

Discover why LLM inference optimization is crucial, identify key performance bottlenecks, measure success, and explore top optimization categories and hands-on profiling techniques.

Discover transformer optimizations: KV Caching for faster generation, GQA for smaller memory footprint, and Flash Attention for faster, efficient attention computation in large language models.

Learn how quantization, pruning, and speculative decoding shrink LLMs and speed up text generation while preserving output quality for more efficient AI deployments.

Learn how to scale and deploy large language models using model parallelism, sharding (DeepSpeed ZeRO/FSDP), and optimized serving tools like TensorRT-LLM, Triton, vLLM, and llama.cpp.