Finding the Pareto Frontier of Low-Precision Data Formats and MAC Architecture for LLM Inference.
Brian Crafton, Xiaochen Peng, Xiaoyu Sun, Ashwin Sanjay Lele, Bo Zhang, Win-San Khwa, Kerem Akarvardar
Browse the full DAC paper archive.
Brian Crafton, Xiaochen Peng, Xiaoyu Sun, Ashwin Sanjay Lele, Bo Zhang, Win-San Khwa, Kerem Akarvardar
Browse the full DAC paper archive.