Hacker News

CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs

arxiv-logo-fb-2

Computer Science > Machine Learning arXiv:2605.19269 (cs) [Submitted on 19 May 2026 (v1), last revised 20 May 2026 (this version, v2)] Title:CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs Authors:Han Guo, Jack Zhang, Arjun Menon, Driss Guessous, Vijay Thakkar, Yoon Kim, Tri Dao View a PDF of the paper titled CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs, by Han Guo and 6 other authors View PDF HTML (experimental) Abstract:Transformer training systems are built around dense linear algebra, yet a nontrivial fraction of end-to-end time is spent on surrounding memory-bound operators. Normalization, activations, residual updates, reductions, and related computations repeatedly move large intermediate tensors through global memory while performing…

Continue reading at Hacker News arxiv.org
Advertisement