Course Websites

Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: 1 to 4 undergraduate hours. 1 to 4 graduate hours. May be repeated in the same or separate terms if topics vary.

The goal of this course is to provide students with an in-depth understanding of various elements of modern machine learning systems, ranging from the performance characteristics of ML models such as transformers and diffusers, performance optimization techniques that reduce the compute, memory, and communication for training and inference of large ML models, and compression algorithms that make ML models smaller and cheaper. The course will also conduct case studies on modern large language model training and serving and cover the design rationale behind state-of-the-art machine learning frameworks. Prerequisites: CS 425, CS 446 For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/ CSregister