CP-Bench: A PyTorch Test Suite to Detect AI Hardware Failure, Performance Degradation, and Silent Data Corruption.
Xun Jiao, Sunny Yang, Suman Gumudavelli, Shreya Varshini, Abhinav Pandey, Abhinav Jauhri, Francesco Caggioni, Gautham Vunnam, Harish Dattatraya Dixit, Jason Liang, Philip Henzler, Sameeksha Gupta, Tyler Graf, Venkat Ramesh, Fan Fred Lin
Browse the full ITC paper archive.