{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/cache-me-if-you-can-how-many-kvs-do-you-need","title":"Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?","arxiv_id":"2506.17121","date":"2025-06-20","proceeding":null,"authors":["Adithya Bhaskar","Alexander Wettig","Tianyu Gao","Yihe Dong","Danqi Chen"],"abstract":"Language models handle increasingly long contexts for tasks such as book summarization, but this leads to growing memory costs for the key-value (KV) cache. Many prior works have proposed ways of discarding KVs from memory, but their approaches are tailored to favorable settings, obscuring caveats like high peak memory and performance degradation, and a fair comparison between methods is difficult. In this paper, we propose the *KV footprint* as a unified metric, which accounts for both the amount of KV entries stored and their lifespan in memory. We evaluate methods based on the smallest footprint they attain while preserving performance in both long-context understanding and generation, with context lengths of up to 128K tokens. This metric reveals the high peak memory of prior KV eviction methods. One class of methods -- *post-fill eviction* -- has a high footprint due to being incompatible with eviction during pre-filling. We adapt these methods to be able to evict KVs during pre-filling, achieving substantially lower KV footprints. We then turn to *recency eviction* methods, wherein we propose PruLong, an end-to-end optimization method for learning which attention heads need to retain the full KV cache and which do not. PruLong saves memory while preserving long-context performance, achieving 12% smaller KV footprint than prior methods while retaining performance in challenging recall tasks. Our paper clarifies the complex tangle of long-context inference methods and paves the way for future development to minimize the KV footprint.","url_abs":"https://arxiv.org/abs/2506.17121v1","url_pdf":"https://arxiv.org/pdf/2506.17121v1.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":"cache-me-if-you-can-how-many-kvs-do-you-need","repo_url":"https://github.com/princeton-pli/prulong","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Book summarization"},{"task_slug":"long-context-understanding","task_name":"Long-Context Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.17121","atlas_url":"https://app.syntology.ai/?focus=2506.17121","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2506.17121"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2506.17121\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2506.17121"},"call":"get_concepts_for_paper(arxiv_id=\"2506.17121\")"}],"by_repo":[{"repo":"princeton-pli/prulong","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.10819"],"harvested_for_calls":[{"arxiv_id":"2410.10819","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.10819"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.10819\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"305f92fce357104fcb8f3c1711c4330bed5bdba80e4516998732bc61f9cc2592","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}