{"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/various-lengths-constant-speed-efficient","title":"Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention","arxiv_id":"2405.17381","date":"2024-05-27","proceeding":null,"authors":["Zhen Qin","Weigao Sun","Dong Li","Xuyang Shen","Weixuan Sun","Yiran Zhong"],"abstract":"We present Lightning Attention, the first linear attention implementation that maintains a constant training speed for various sequence lengths under fixed memory consumption. Due to the issue with cumulative summation operations (cumsum), previous linear attention implementations cannot achieve their theoretical advantage in a casual setting. However, this issue can be effectively solved by utilizing different attention calculation strategies to compute the different parts of attention. Specifically, we split the attention calculation into intra-blocks and inter-blocks and use conventional attention computation for intra-blocks and linear attention kernel tricks for inter-blocks. This eliminates the need for cumsum in the linear attention calculation. Furthermore, a tiling technique is adopted through both forward and backward procedures to take full advantage of the GPU hardware. To enhance accuracy while preserving efficacy, we introduce TransNormerLLM (TNL), a new architecture that is tailored to our lightning attention. We conduct rigorous testing on standard and self-collected datasets with varying model sizes and sequence lengths. TNL is notably more efficient than other language models. In addition, benchmark results indicate that TNL performs on par with state-of-the-art LLMs utilizing conventional transformer structures. The source code is released at github.com/OpenNLPLab/TransnormerLLM.","url_abs":"https://arxiv.org/abs/2405.17381v2","url_pdf":"https://arxiv.org/pdf/2405.17381v2.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":"various-lengths-constant-speed-efficient","repo_url":"https://github.com/opennlplab/transnormerllm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.17381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17381"}},"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":"deterministic:regex_extraction","url":"https://github.com/OpenNLPLab/TransnormerLLM","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opennlplab/transnormerllm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"community":{"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":"5c5247729979fd74","entry":"jload","repo":"opennlplab/transnormerllm","repo_kind":"official","path":"fine-tune/utils.py","file_url":"https://github.com/opennlplab/transnormerllm/blob/HEAD/fine-tune/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c5247729979fd74"}},{"code_sha256_prefix":"e1bc11231701a60b","entry":"get_full_mask","repo":"OpenNLPLab/lightning-attention","repo_kind":"community","path":"lightning_attn/ops/torch/linear_attention.py","file_url":"https://github.com/OpenNLPLab/lightning-attention/blob/HEAD/lightning_attn/ops/torch/linear_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1bc11231701a60b"}},{"code_sha256_prefix":"da98a1df7821aa3e","entry":"get_mask","repo":"OpenNLPLab/lightning-attention","repo_kind":"community","path":"lightning_attn/ops/torch/linear_attention.py","file_url":"https://github.com/OpenNLPLab/lightning-attention/blob/HEAD/lightning_attn/ops/torch/linear_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da98a1df7821aa3e"}},{"code_sha256_prefix":"d07d04439cd1d44f","entry":"jload","repo":"OpenNLPLab/TransnormerLLM","repo_kind":"official","path":"fine-tune/utils.py","file_url":"https://github.com/OpenNLPLab/TransnormerLLM/blob/HEAD/fine-tune/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"code_sha256_prefix":"575cd309f151c9a9","entry":"linear_attn","repo":"OpenNLPLab/lightning-attention","repo_kind":"community","path":"lightning_attn/ops/torch/linear_attention.py","file_url":"https://github.com/OpenNLPLab/lightning-attention/blob/HEAD/lightning_attn/ops/torch/linear_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"575cd309f151c9a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}