Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chai, Duo, Liu, Zizhen, Wang, Shuhuai, Pei, Songwei, Liu, Cheng, Li, Huawei, Wang, Shangguang
Format:	Preprint
Published:	2025
Subjects:	Hardware Architecture Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.19912