Course Websites

CS 598 AIE - AI Efficiency: Sys. & Algor.

Last offered Fall 2024

Official Description

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: May be repeated in the same or separate terms if topics vary.

Section Description

Topic: AI Efficiency: Systems & Algorithms Are you curious about how system techniques enable today's large-scale model training and deliver ultra-fast inference? Do you have a passion for making AI accessible to all by using advanced system and algorithm techniques, thereby significantly reducing the cost of training and deploying deep learning models? If so, this course is for you. The course provides an in-depth view of AI efficiency, focusing on the core concepts of both AI systems and algorithmic methods. We will explore and discuss seminal works in the field of AI systems, such as ZeRO-style data parallelism, tensor parallelism, pipeline parallelism, sequence parallelism, and 3D parallelism. We will also go over inference optimization techniques, such as FlashAttention, blocked KV cache, speculative decoding, and various compression algorithms. Students will have the opportunity to present existing works in the field of AI efficiency and learn to write paper reviews, which help d

Related Faculty

AI Efficiency: Sys. & Algor.AIE46989S441230 - 1345 W F  1302 Siebel Center for Comp Sci Minjia Zhang