Papers › Generating Long Sequences with Sparse Transformers

Generating Long Sequences with Sparse Transformers

23 Apr 2019Preprint 2019 4arXiv:1904.10509archive 2025-07-28

Rewon Child, Scott Gray, Alec Radford, Ilya Sutskever

Transformers are powerful sequence models, but require time and memory that grows quadratically with the sequence length. In this paper we introduce sparse factorizations of the attention matrix which reduce this to O(n √(n)). We also introduce a) a variation on architecture and initialization to train deeper networks, b) the recomputation of attention matrices to save memory, and c) fast attention kernels for training. We call networks with these changes Sparse Transformers, and show they can model sequences tens of thousands of timesteps long using hundreds of layers. We use the same architecture to model images, audio, and text from raw bytes, setting a new state of the art for density modeling of Enwik8, CIFAR-10, and ImageNet-64. We generate unconditional samples that demonstrate global coherence and great diversity, and show it is possible in principle to use self-attention to model sequences of length one million or more.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1904.10509")

Code

Syntology Ran 5 of 6 code samples harvested from 2 repositories linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: community (archive-listed): 6 samples from 2 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

openai/sparse_attention officialmentioned on GitHubtf report
han-shi/SparseBERT mentioned on GitHubpytorch report
mistralai/mistral-src mentioned on GitHubpytorchApache-2.0 report
ptillet/torch-blocksparse mentioned on GitHubpytorch report
wilson1yan/VideoGPT mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 5 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
4ran
1unverified

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

DeepSpeedSparseSelfAttention ptillet/torch-blocksparse/torch_blocksparse/deepspeedsparseselfattention.py community (archive-listed) ran MIT (permissive) · cc4d4565045cf844 · report
SparseAttention wilson1yan/VideoGPT/videogpt/attention.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 21937d73418cc532 · report
SparsityConfig ptillet/torch-blocksparse/torch_blocksparse/deepspeedsparseselfattention.py community (archive-listed) ran MIT (permissive) · 23a25a6d256367d8 · report
StridedSparsityConfig wilson1yan/VideoGPT/videogpt/attention.py community (archive-listed) ran MIT (permissive) · b5ef9bf53e62eab3 · report
scaled_dot_product_attention wilson1yan/VideoGPT/videogpt/attention.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9d35276799c65577 · report
view_range wilson1yan/VideoGPT/videogpt/attention.py community (archive-listed) unverified MIT (permissive) · 9f28796c8276d371 · report

Tasks

DiversityImage GenerationLanguage ModellingOpen-Domain Question AnsweringQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio Generation Classical music, 5 seconds at 12 kHz Sparse Transformer 152M (strided) Bits per byte 1.97 #1 of 2 Archive leaderboard report
Image Generation ImageNet 64x64 Sparse Transformer 59M (strided) Bits per dim 3.44 #43 of 65 Archive leaderboard report
Language Modelling enwik8 Sparse Transformer (30 layers, fixed attn) Bit per Character (BPC) 0.99 #14 of 42 Archive leaderboard report
Language Modelling enwik8 Sparse Transformer (30 layers, fixed attn) Number of params 95M #14 of 42 Archive leaderboard report
Open-Domain Question Answering SearchQA Sparse Attention EM 64.7 #4 of 14 Archive leaderboard report
Question Answering Natural Questions (long) Sparse Attention F1 74.5 #4 of 13 Archive leaderboard report
Question Answering Quasart-T Sparse Attention EM 52.1 #3 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutCosine AnnealingDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxSparse TransformerWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections