{"ID":2891861,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16676","arxiv_id":"2507.16676","title":"Custom Algorithm-based Fault Tolerance for Attention Layers in Transformers","abstract":"Transformers and large language models (LLMs), powered by the attention mechanism, have transformed numerous AI applications, driving the need for specialized hardware accelerators. A major challenge in these accelerators is efficiently detecting errors caused by random hardware faults. Traditional algorithm-based fault tolerance (ABFT) techniques verify individual matrix multiplications but fall short in handling the full attention mechanism, particularly due to intermediate softmax normalization. This work proposes Flash-ABFT, a novel method that computes an online checksum across the entire three-matrix product of query, key and value matrices, of an attention layer, including the softmax operation, with a single check. This approach significantly reduces overhead by eliminating redundant checks while maintaining high fault-detection accuracy. Experimental results demonstrate that Flash-ABFT incurs only 5.3% hardware area overhead and less than 1.9% energy overhead, making it a cost-effective and robust solution for error detection in attention accelerators.","short_abstract":"Transformers and large language models (LLMs), powered by the attention mechanism, have transformed numerous AI applications, driving the need for specialized hardware accelerators. A major challenge in these accelerators is efficiently detecting errors caused by random hardware faults. Traditional algorithm-based faul...","url_abs":"https://arxiv.org/abs/2507.16676","url_pdf":"https://arxiv.org/pdf/2507.16676v1","authors":"[\"Vasileios Titopoulos\",\"Kosmas Alexandridis\",\"Giorgos Dimitrakopoulos\"]","published":"2025-07-22T15:11:13Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AR\"]","methods":"[\"Transformer\",\"Large Language Model\",\"Language Model\"]","has_code":false}