{"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":"/method/multi-query-attention","slug":"multi-query-attention","name":"Multi-Query Attention","full_name":"Multi-Query Attention","full_name_withheld":false,"description_markdown":"Multi-head attention consists of multiple attention layers (heads) in parallel with different linear\r\ntransformations on the queries, keys, values and outputs. **Multi-query attention** is identical except that the\r\ndifferent heads share a single set of keys and values.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/1911.02150v1","title":"Fast Transformer Decoding: One Write-Head is All You Need","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Attention","url":"/methods/category/attention","pwc_aliases":[]}],"n_papers_tagged":13,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"the-nature-of-mathematical-modeling-and","title":"The Nature of Mathematical Modeling and Probabilistic Optimization Engineering in Generative AI","date":"2024-10-24","arxiv_id":"2410.18441","n_code_links":0,"syntology":null},{"paper":null,"slug":"weighted-grouped-query-attention-in","title":"Weighted Grouped Query Attention in Transformers","date":"2024-07-15","arxiv_id":"2407.10855","n_code_links":0,"syntology":null},{"paper":"/paper/mlkv-multi-layer-key-value-heads-for-memory","slug":"mlkv-multi-layer-key-value-heads-for-memory","title":"MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding","date":"2024-06-13","arxiv_id":"2406.09297","n_code_links":1,"syntology":null},{"paper":null,"slug":"effectively-compress-kv-heads-for-llm","title":"Effectively Compress KV Heads for LLM","date":"2024-06-11","arxiv_id":"2406.07056","n_code_links":0,"syntology":null},{"paper":null,"slug":"qcqa-quality-and-capacity-aware-grouped-query","title":"QCQA: Quality and Capacity-aware grouped Query Attention","date":"2024-06-08","arxiv_id":"2406.10247","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-transformer-key-value-cache-size","slug":"reducing-transformer-key-value-cache-size","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","date":"2024-05-21","arxiv_id":"2405.12981","n_code_links":2,"syntology":null},{"paper":null,"slug":"bifurcated-attention-for-single-context-large","title":"Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs","date":"2024-03-13","arxiv_id":"2403.08845","n_code_links":0,"syntology":null},{"paper":"/paper/griffin-mixing-gated-linear-recurrences-with","slug":"griffin-mixing-gated-linear-recurrences-with","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","date":"2024-02-29","arxiv_id":"2402.19427","n_code_links":4,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/gqa-training-generalized-multi-query","slug":"gqa-training-generalized-multi-query","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","date":"2023-05-22","arxiv_id":"2305.13245","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/flashattention-fast-and-memory-efficient","slug":"flashattention-fast-and-memory-efficient","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","date":"2022-05-27","arxiv_id":"2205.14135","n_code_links":13,"syntology":{"ran":24,"of":30,"n_ran_checked":18,"n_instrument":6,"unverified":6,"pointer_only":1,"phrase":"24 ran (of which 2 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["dao-ailab/flash-attention"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed"]}}},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","n_code_links":7,"syntology":{"ran":32,"of":37,"n_ran_checked":24,"n_instrument":8,"unverified":5,"pointer_only":0,"phrase":"32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":"/paper/fast-transformer-decoding-one-write-head-is","slug":"fast-transformer-decoding-one-write-head-is","title":"Fast Transformer Decoding: One Write-Head is All You Need","date":"2019-11-06","arxiv_id":"1911.02150","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/mastering-chess-and-shogi-by-self-play-with-a","slug":"mastering-chess-and-shogi-by-self-play-with-a","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","date":"2017-12-05","arxiv_id":"1712.01815","n_code_links":62,"syntology":{"ran":13,"of":17,"n_ran_checked":4,"n_instrument":9,"unverified":4,"pointer_only":9,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified","official":null}}],"papers_shown":13,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":13,"with_a_code_link":8,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":13,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/method/multi-query-attention/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/multi-query-attention/papers/ran/1","json":"/method/multi-query-attention/papers/ran/1.json","rows":6}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":6},{"task":"/task/language-modeling","name":"Language Modeling","papers":3},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/16k","name":"16k","papers":1},{"task":"/task/4k","name":"4k","papers":1},{"task":null,"name":"8k","papers":1},{"task":"/task/all","name":"All","papers":1},{"task":"/task/answer-generation","name":"Answer Generation","papers":1},{"task":"/task/auto-debugging","name":"Auto Debugging","papers":1},{"task":"/task/code-generation","name":"Code Generation","papers":1},{"task":"/task/common-sense-reasoning","name":"Common Sense Reasoning","papers":1},{"task":"/task/coreference-resolution","name":"Coreference Resolution","papers":1},{"task":"/task/cross-lingual-question-answering","name":"Cross-Lingual Question Answering","papers":1},{"task":"/task/document-classification","name":"Document Classification","papers":1},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/game-of-chess","name":"Game of Chess","papers":1},{"task":"/task/game-of-go","name":"Game of Go","papers":1},{"task":"/task/game-of-shogi","name":"Game of Shogi","papers":1},{"task":"/task/general-reinforcement-learning","name":"General Reinforcement Learning","papers":1}],"tasks_shown":20,"n_tasks":44,"usage_by_year":[{"year":"2017","papers":1},{"year":"2019","papers":1},{"year":"2022","papers":2},{"year":"2023","papers":1},{"year":"2024","papers":8}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/multi-query-attention"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Multi-Query%20Attention","read_at":"2026-10-05T00:59:24+00:00","query":"Multi-Query Attention","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Multi-Query Attention' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["multi-axis attention","Fuzzy Query Attention","Multi-class Label Query","Multi-Stage Attention-GAN","Multi-Block Attention (MBA)","Multipole Semantic Attention","Multi-Time Attention Networks","Grouped-Query Attention (GQA)"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"9f0fbf908ea116988ce2e0339dbfb0b3cd78225fbb236d49805eed9419cf27f4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}