{"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/reducing-transformer-key-value-cache-size","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","arxiv_id":"2405.12981","date":"2024-05-21","proceeding":null,"authors":["William Brandon","Mayank Mishra","Aniruddha Nrusimha","Rameswar Panda","Jonathan Ragan Kelly"],"abstract":"Key-value (KV) caching plays an essential role in accelerating decoding for transformer-based autoregressive large language models (LLMs). However, the amount of memory required to store the KV cache can become prohibitive at long sequence lengths and large batch sizes. Since the invention of the transformer, two of the most effective interventions discovered for reducing the size of the KV cache have been Multi-Query Attention (MQA) and its generalization, Grouped-Query Attention (GQA). MQA and GQA both modify the design of the attention block so that multiple query heads can share a single key/value head, reducing the number of distinct key/value heads by a large factor while only minimally degrading accuracy. In this paper, we show that it is possible to take Multi-Query Attention a step further by also sharing key and value heads between adjacent layers, yielding a new attention design we call Cross-Layer Attention (CLA). With CLA, we find that it is possible to reduce the size of the KV cache by another 2x while maintaining nearly the same accuracy as unmodified MQA. In experiments training 1B- and 3B-parameter models from scratch, we demonstrate that CLA provides a Pareto improvement over the memory/accuracy tradeoffs which are possible with traditional MQA, enabling inference with longer sequence lengths and larger batch sizes than would otherwise be possible","url_abs":"https://arxiv.org/abs/2405.12981v1","url_pdf":"https://arxiv.org/pdf/2405.12981v1.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":"reducing-transformer-key-value-cache-size","repo_url":"https://github.com/ibm/dolomite-engine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"reducing-transformer-key-value-cache-size","repo_url":"https://github.com/whyNLP/LCKV","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"grouped-query-attention","method_name":"Grouped-query attention"},{"method_slug":"multi-query-attention","method_name":"Multi-Query Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.12981","atlas_url":"https://app.syntology.ai/?focus=2405.12981","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":"2405.12981"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2405.12981\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2405.12981"},"call":"get_concepts_for_paper(arxiv_id=\"2405.12981\")"}],"by_repo":[{"repo":"ibm/dolomite-engine","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.17980"],"harvested_for_calls":[{"arxiv_id":"2410.17980","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.17980"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.17980\")"}]},{"repo":"whyNLP/LCKV","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.14442"],"harvested_for_calls":[{"arxiv_id":"2410.14442","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.14442"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.14442\")"}]}],"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":"169ce7aabf7082655b7c89ef3ad722fcf0ea8cb5b2487868b982bca46cc62b0d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}