{"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/rethinking-key-value-cache-compression","title":"Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving","arxiv_id":"2503.24000","date":"2025-03-31","proceeding":null,"authors":["Wei Gao","Xinyu Zhou","Peng Sun","Tianwei Zhang","Yonggang Wen"],"abstract":"Key-Value cache (\\texttt{KV} \\texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory consumption of \\texttt{KV} \\texttt{cache} to reduce the computation cost. Despite the development of many compression algorithms, their applications in production environments are still not prevalent. In this paper, we revisit mainstream \\texttt{KV} \\texttt{cache} compression solutions from a practical perspective. Our contributions are three-fold. First, we comprehensively review existing algorithmic designs and benchmark studies for \\texttt{KV} \\texttt{cache} compression and identify missing pieces in their performance measurement, which could hinder their adoption in practice. Second, we empirically evaluate representative \\texttt{KV} \\texttt{cache} compression methods to uncover two key issues that affect the computational efficiency: (1) while compressing \\texttt{KV} \\texttt{cache} can reduce memory consumption, current implementations (e.g., FlashAttention, PagedAttention) do not optimize for production-level LLM serving, resulting in suboptimal throughput performance; (2) compressing \\texttt{KV} \\texttt{cache} may lead to longer outputs, resulting in increased end-to-end latency. We further investigate the accuracy performance of individual samples rather than the overall performance, revealing the intrinsic limitations in \\texttt{KV} \\texttt{cache} compression when handling specific LLM tasks. Third, we provide tools to shed light on future \\texttt{KV} \\texttt{cache} compression studies and facilitate their practical deployment in production. They are open-sourced in \\href{https://github.com/LLMkvsys/rethink-kv-compression}{https://github.com/LLMkvsys/rethink-kv-compression}.","url_abs":"https://arxiv.org/abs/2503.24000v1","url_pdf":"https://arxiv.org/pdf/2503.24000v1.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":"rethinking-key-value-cache-compression","repo_url":"https://github.com/llmkvsys/rethink-kv-compression","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.24000","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}