all AI news
SoD$^2$: Statically Optimizing Dynamic Deep Neural Network
March 4, 2024, 5:41 a.m. | Wei Niu, Gagan Agrawal, Bin Ren
cs.LG updates on arXiv.org arxiv.org
Abstract: Though many compilation and runtime systems have been developed for DNNs in recent years, the focus has largely been on static DNNs. Dynamic DNNs, where tensor shapes and sizes and even the set of operators used are dependent upon the input and/or execution, are becoming common. This paper presents SoD$^2$, a comprehensive framework for optimizing Dynamic DNNs. The basis of our approach is a classification of common operators that form DNNs, and the use of …
abstract arxiv compilation cs.ai cs.lg cs.pl deep neural network dynamic focus network neural network operators paper set systems tensor type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote