The paper demonstrates that large‑language models can be trained to tolerate unreliable computer hardware, with their error resilience improving as the models grow. Using 40,000 GPU‑hours of training on simulated faulty hardware, the authors derive modified neural scaling laws that show models learn to compute within efficient error‑correcting codes. This suggests that, if formally fault‑tolerant, such models could enable AI inference on low‑energy, faulty hardware, potentially yielding significant energy savings.
By Trevor McCourt, Ila R. Fiete, Isaac L. Chuang
arXiv:2610.07029v1 Announce Type: cross
Abstract: Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising platform for processing massively memory intensive...
By Aniseh Dorostkar, Hamed Farbeh, Hamid R. Zarandi
arXiv:2603.24595v2 Announce Type: replace-cross
Abstract: Large language model (LLM) inference systems rely on CUDA kernels for core GPU computations, yet the interface between models and kernels is...
By Mengting He, Shihao Xia, Haomin Jia, Wenfei Wu, Linhai Song
arXiv:2606. 02430v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into high-performance computing (HPC) workflows, accelerating scientific discovery through diverse perspectives such as code generation and domain-specific decision-making.
By Yafan Huang, Sheng Di, Guanpeng Li
arXiv:2606. 20128v1 Announce Type: cross Abstract: Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks.
By Dipankar Sarkar
arXiv:2610.14009v1 Announce Type: cross
Abstract: Large AI models increasingly rely on distributed GPU execution, yet it remains unclear whether established failure analysis methods transfer effectiv...
By Boyuan Cui, Yuyang Zeng, Yifang Tian, Hans-Arno Jacobsen
arXiv:2607. 01646v2 Announce Type: replace Abstract: State-of-the-art large language model (LLM) training takes tens of thousands of graphics processing units (GPUs) for months and encounters failures across the software and hardware stack.
By Haotian Xie, Junlin Chen, Mingkai Zheng, Lishan Yang, Zhao Zhang
arXiv:2609.16742v1 Announce Type: cross
Abstract: Convolutional Neural Networks (CNNs) are increasingly deployed in safety-critical edge applications, where soft errors can silently corrupt inference...
By Kyrylo Nazarevych, Mohammad Hasan Ahmadilivani, Krister Kaldre, Davide Bertozzi, Jaan Raik
RobustNCL is a lightweight framework that enhances the reliability of neuromorphic continual learning (NCL) systems against transient hardware faults. It detects faults during weight access from off‑chip memory and cures affected weights using one of three strategies—zero replacement, min/max value, or most‑probable value—storing curing values in radiation‑hardened memory. Experiments on Split MNIST, Split Fashion‑MNIST, Split CIFAR‑10, and Split CIFAR‑100 show that RobustNCL maintains accuracy within 0.5% of fault‑free models and significantly outperforms baseline NCL methods while adding negligible latency and energy overhead.
By Rachmad Vidya Wicaksana Putra, Shuochen Zhou, Muhammad Shafique
The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprint of deployed AI systems. However, direct measurement of inference energy often requires hardware telemetry, power instrumentation, or infrastructure-specific monitoring, limiting its applicability in comparative studies, early-stage system design, and sustainability reporting.
arXiv:2607. 26571v1 Announce Type: new Abstract: The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprint of deployed AI systems.
By Tina Vartziotis, Rodopi Kosteli, Elli Vartziotis, George Dasoulas, Michael Keckeisen, Konstantinos Skianis, Sotirios Kotsopoulos, Francesca Dominici
arXiv:2607. 19623v1 Announce Type: cross Abstract: We characterize per-bit-position fault sensitivity in ML inference across 16 workloads -- spanning transformer-based models and attention-free CNNs -- and across three floating-point formats.
By Muhammad Husnain Mubarik, Karthik Mohan Kumar, Pedro Antonio Pena, Keshavan Varadarajan, Kunal Tyagi