Explore offloading-efficient sparse AI systems in this 19-minute conference talk presented at the SPARSE 2024 workshop. Gain insights from speaker Luo Mai as they delve into cutting-edge techniques for optimizing sparse artificial intelligence architectures. Learn about the latest advancements in offloading strategies designed to enhance the efficiency of sparse AI models. Discover how these approaches can potentially improve performance and resource utilization in AI systems. Understand the implications of this research for the future development of more efficient and scalable AI technologies. Engage with content from the SPARSE workshop, part of the ACM SIGPLAN-sponsored PLDI 2024 conference, focusing on innovations in sparse computing for AI applications.
Overview
Syllabus
[SPARSE24] Offloading-Efficient Sparse AI Systems
Taught by
ACM SIGPLAN
Related Courses
-
Exploiting Sparsity and Redundancy - SPARSE 2024
-
Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations
-
Software and Hardware for Sparse Machine Learning
-
PockEngine: Sparse and Efficient Fine-tuning in a Pocket
-
Challenges with Hardware-Software Co-design for Sparse Machine Learning on Dataflow Architectures
-
General Distributed Framework for Contraction of Sparse Tensor with Tensor Network
