@misc{indiciae5aea8fd30ad0, title = {ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training}, author = {Liang, Yuhang [University of Alabama - Birmingham] and Li, Xinyi [BATTELLE (PACIFIC NW LAB)] and Ren, Jie [College of William and Mary in Virginia] and Li, Ang [BATTELLE (PACIFIC NW LAB)] and Fang, Bo [BATTELLE (PACIFIC NW LAB)] and Chen, Jieyang [University of Alabama - Birmingham]}, year = {2025}, doi = {10.1145/3710848.3710870}, url = {https://www.osti.gov/biblio/2545654}, note = {Source identifier: 2545654} }