Work in Progress: Real-time Transformer Inference on Edge AI Accelerators.
Brendan Reidy, Mohammadreza Mohammadi, Mohammed E. Elbtity, Heath Smith, Ramtin Zand
Browse the full RTAS paper archive.
Brendan Reidy, Mohammadreza Mohammadi, Mohammed E. Elbtity, Heath Smith, Ramtin Zand
Browse the full RTAS paper archive.