FT2: First-Token-Inspired Online Fault Tolerance on Critical Layers for Generative Large Language Models.
Yu Sun, Zhu Zhu, Cherish Mulpuru, Roberto Gioiosa, Zhao Zhang, Bo Fang, Lishan Yang
Browse the full HPDC paper archive.
Yu Sun, Zhu Zhu, Cherish Mulpuru, Roberto Gioiosa, Zhao Zhang, Bo Fang, Lishan Yang
Browse the full HPDC paper archive.