Work in Progress: Real-time Transformer Inference on Edge AI Accelerators

Brendan Reidy, Mohammadreza Mohammadi, Mohammed E. Elbtity, Heath Smith, Ramtin Zand. Work in Progress: Real-time Transformer Inference on Edge AI Accelerators. In 29th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2023, San Antonio, TX, USA, May 9-12, 2023. pages 341-344, IEEE, 2023. [doi]

Abstract

Abstract is missing.