Papers › Fastformer: Additive Attention Can Be All You Need

Fastformer: Additive Attention Can Be All You Need

20 Aug 2021arXiv:2108.09084archive 2025-07-28

Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang, Xing Xie

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on long sequences or not effective enough. In this paper, we propose Fastformer, which is an efficient Transformer model based on additive attention. In Fastformer, instead of modeling the pair-wise interactions between tokens, we first use additive attention mechanism to model global contexts, and then further transform each token representation based on its interaction with global context representations. In this way, Fastformer can achieve effective context modeling with linear complexity. Extensive experiments on five datasets show that Fastformer is much more efficient than many existing Transformer models and can meanwhile achieve comparable or even better long text modeling performance.

PaperPDFCodeCode 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="2108.09084")

Code

Syntology Ran 4 of 4 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · violated contract; 2 ran · our draft was wrong.

By repository: community (archive-listed): 1 sample from 1 repository, 1 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

13 repositories listed; official and paper-mentioned ones first.

wuch15/Fastformer officialmentioned in paperpytorch report
04RR/SOTA-Vision mentioned on GitHubpytorch report
Rishit-dagli/Fast-Transformer mentioned on GitHubtfApache-2.0 report
lucidrains/fast-transformer-pytorch mentioned on GitHubpytorch report
mtanghu/LEAP mentioned on GitHubpytorchCC0-1.0 report
rainyBJ/Fastformer-Paddle mentioned on GitHubpaddle report
wilile26811249/Fastformer-PyTorch mentioned on GitHubpytorchMIT report
ypeleg/Fastformer-Keras mentioned on GitHubtf 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

4 samples harvested; 4 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
2ran · our draft was wrong

Licence: 3 of the 4 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 lucidrains/fast-transformer-pytorch. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

FeedForward lucidrains/fast-transformer-pytorch/fast_transformer_pytorch/fast_transformer_pytorch.py community (archive-listed) ran · our draft was wrong MIT (permissive) · a7b572de5bd1ac1d · report
default identical code first harvested elsewhere ran · violated contract fingerprinted licence of this copy not recorded · 60fff7c3c400d7ff · report
exists identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · aa5486a3650902d8 · report
read_lexicon identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 2b5c06c1ba593c3c · report

Tasks

AllNews RecommendationText ClassificationText Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Summarization CNN / Daily Mail (Anonymized) Fastformer ROUGE-1 38.54 #11 of 13 Archive leaderboard report
Text Summarization CNN / Daily Mail (Anonymized) Fastformer ROUGE-2 16.22 #11 of 13 Archive leaderboard report
Text Summarization CNN / Daily Mail (Anonymized) Fastformer ROUGE-L 36.21 #11 of 13 Archive leaderboard report
Text Summarization Pubmed Fastformer ROUGE-1 38.09 #28 of 29 Archive leaderboard report
Text Summarization Pubmed Fastformer ROUGE-2 15.44 #28 of 29 Archive leaderboard report
Text Summarization Pubmed Fastformer ROUGE-L 34.81 #28 of 29 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

Introduced by this paper: Fastformer

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFastformerLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTanh ActivationTransformer

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