{"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/sparq-attention-bandwidth-efficient-llm","title":"SparQ Attention: Bandwidth-Efficient LLM Inference","arxiv_id":"2312.04985","date":"2023-12-08","proceeding":null,"authors":["Luka Ribar","Ivan Chelombiev","Luke Hudlass-Galley","Charlie Blake","Carlo Luschi","Douglas Orr"],"abstract":"The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically causes token-generation to be bottlenecked by data transfer. For this reason, we introduce SparQ Attention, a technique for increasing the inference throughput of LLMs by utilising memory bandwidth more efficiently within the attention layers, through selective fetching of the cached history. Our proposed technique can be applied directly to off-the-shelf LLMs during inference, without requiring any modification to the pre-training setup or additional fine-tuning. We show that SparQ Attention brings up to 8x savings in attention data transfers without substantial drops in accuracy, by evaluating Llama 2 and 3, Mistral, Gemma and Pythia models on a wide range of downstream tasks.","url_abs":"https://arxiv.org/abs/2312.04985v6","url_pdf":"https://arxiv.org/pdf/2312.04985v6.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":"sparq-attention-bandwidth-efficient-llm","repo_url":"https://github.com/graphcore-research/llm-inference-research","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":[{"method_slug":"pythia","method_name":"Pythia"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.04985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04985"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/graphcore-research/llm-inference-research","reach":null}],"summary":{"ran_violates":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"86940e44a1e04d87","entry":"causal_index","repo":"graphcore-research/llm-inference-research","repo_kind":"official","path":"llminference/methods/sparse_attention.py","file_url":"https://github.com/graphcore-research/llm-inference-research/blob/HEAD/llminference/methods/sparse_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86940e44a1e04d87"}},{"code_sha256_prefix":"4a773d83528b1d76","entry":"score_to_mask","repo":"graphcore-research/llm-inference-research","repo_kind":"official","path":"llminference/methods/sparse_attention.py","file_url":"https://github.com/graphcore-research/llm-inference-research/blob/HEAD/llminference/methods/sparse_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a773d83528b1d76"}},{"code_sha256_prefix":"441b1499530225b2","entry":"topk_mask","repo":"graphcore-research/llm-inference-research","repo_kind":"official","path":"llminference/methods/sparse_attention.py","file_url":"https://github.com/graphcore-research/llm-inference-research/blob/HEAD/llminference/methods/sparse_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"441b1499530225b2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}