{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/top-theta-attention-sparsifying-transformers","title":"Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding","arxiv_id":"2502.08363","date":"2025-02-12","proceeding":null,"authors":["Konstantin Berestizshevsky","Renzo Andri","Lukas Cavigelli"],"abstract":"The attention mechanism is essential for the impressive capabilities of transformer-based Large Language Models (LLMs). However, calculating attention is computationally intensive due to its quadratic dependency on the sequence length. We introduce a novel approach called Top-Theta Attention, or simply Top-$\\theta$, which selectively prunes less essential attention elements by comparing them against carefully calibrated thresholds. This method greatly improves the efficiency of self-attention matrix multiplication while preserving model accuracy, reducing the number of required V cache rows by 3x during generative decoding and the number of attention elements by 10x during the prefill phase. Our method does not require model retraining; instead, it requires only a brief calibration phase to be resilient to distribution shifts, thus not requiring the thresholds for different datasets to be recalibrated. Unlike top-k attention, Top-$\\theta$ eliminates full-vector dependency, making it suitable for tiling and scale-out and avoiding costly top-k search. A key innovation of our approach is the development of efficient numerical compensation techniques, which help preserve model accuracy even under aggressive pruning of attention scores.","url_abs":"https://arxiv.org/abs/2502.08363v1","url_pdf":"https://arxiv.org/pdf/2502.08363v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"top-theta-attention-sparsifying-transformers","repo_url":"https://github.com/kostyanoob/top-theta-attention","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}