{"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/buzz-beehive-structured-sparse-kv-cache-with","title":"BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference","arxiv_id":"2410.23079","date":"2024-10-30","proceeding":null,"authors":["Junqi Zhao","Zhijin Fang","Shu Li","Shaohui Yang","Shichao He"],"abstract":"Large language models (LLMs) are essential in natural language processing but often struggle with inference speed and computational efficiency, limiting real-time deployment. The key-value (KV) cache mechanism reduces computational overhead in transformer models, but challenges in maintaining contextual understanding remain. In this paper, we propose BUZZ, a novel KV caching algorithm that leverages structured contextual information to minimize cache memory usage while enhancing inference speed. BUZZ employs a beehive-structured sparse cache, incorporating a sliding window to capture recent information and dynamically segmenting historical tokens into chunks to prioritize important tokens in local neighborhoods. We evaluate BUZZ on four real-world datasets: CNN/Daily Mail, XSUM, Wikitext, and 10-QA. Our results demonstrate that BUZZ (1) reduces cache memory usage by $\\textbf{2.5}\\times$ in LLM inference while maintaining over 99% accuracy in long-text summarization, and (2) surpasses state-of-the-art performance in multi-document question answering by $\\textbf{7.69%}$ under the same memory limit, where full cache methods encounter out-of-memory issues. Additionally, BUZZ achieves significant inference speedup with a $\\log{n}$ time complexity. The code is available at https://github.com/JunqiZhao888/buzz-llm.","url_abs":"https://arxiv.org/abs/2410.23079v1","url_pdf":"https://arxiv.org/pdf/2410.23079v1.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":"buzz-beehive-structured-sparse-kv-cache-with","repo_url":"https://github.com/junqizhao888/buzz-llm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.23079","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}