Papers › Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured...

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

31 May 2024arXiv:2405.21060archive 2025-07-28

Tri Dao, Albert Gu

While Transformers have been the main architecture behind deep learning's success in language modeling, state-space models (SSMs) such as Mamba have recently been shown to match or outperform Transformers at small to medium scale. We show that these families of models are actually quite closely related, and develop a rich framework of theoretical connections between SSMs and variants of attention, connected through various decompositions of a well-studied class of structured semiseparable matrices. Our state space duality (SSD) framework allows us to design a new architecture (Mamba-2) whose core layer is an a refinement of Mamba's selective SSM that is 2-8X faster, while continuing to be competitive with Transformers on language modeling.

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="2405.21060")

Code

Syntology Ran 6 of 13 code samples harvested from 4 repositories linked to this paper; 7 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 11 samples from 3 repositories, 4 ran; 1 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.

state-spaces/mamba officialmentioned in papermentioned on GitHubpytorch report
lions-epfl/lion mentioned on GitHubpytorch report
radarFudan/mamba mentioned on GitHubpytorchApache-2.0 report
rorschach1989/transformer-for-gmm mentioned on GitHubpytorchMIT report
tommyip/mamba2-minimal mentioned on GitHubpytorchApache-2.0 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

13 samples harvested; 6 ran; 0 honoured the contract we drafted; 7 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.

3ran · our draft was wrong
3ran
7unverified

Licence: 1 of the 13 samples is 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 4 repositories linked to this paper, official or community; each sample names its own and says which. 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.

heavy_tail_activation state-spaces/mamba/mamba_ssm/modules/mamba3.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5c853f3f04ddb483 · report
segsum radarFudan/mamba/mamba_ssm/modules/ssd_minimal.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · ef936c81f5d4c41c · report
segsum_unstable radarFudan/mamba/mamba_ssm/modules/ssd_minimal.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · f641b66c642a2908 · report
silu tommyip/mamba2-minimal/mamba2.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 8558535d4b8ed416 · report
ssd_minimal_discrete radarFudan/mamba/mamba_ssm/modules/ssd_minimal.py community (archive-listed) ran Apache-2.0 (permissive) · f5c3ef656ef76878 · report
all_gather_raw radarFudan/mamba/mamba_ssm/distributed/distributed_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 0f2196b3902caf16 · report
all_reduce_raw radarFudan/mamba/mamba_ssm/distributed/distributed_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · a06d70b09eb46b60 · report
concat_task_sample rorschach1989/transformer-for-gmm/tgmm/task.py community (archive-listed) unverified MIT (permissive) · 389b08cfb8b3130b · report
concat_task_sample_hf rorschach1989/transformer-for-gmm/tgmm/task.py community (archive-listed) unverified MIT (permissive) · f23bd7f5b8889fa3 · report
concat_task_sample_instruct rorschach1989/transformer-for-gmm/tgmm/task.py community (archive-listed) unverified MIT (permissive) · 32968cc3a1d4a2e0 · report
gen_name_from_cfg rorschach1989/transformer-for-gmm/tgmm/utils/configuration.py community (archive-listed) unverified MIT (permissive) · 2ef6cf3e9fce8a55 · report
reduce_scatter_raw radarFudan/mamba/mamba_ssm/distributed/distributed_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 2d002bb9a87211b8 · report
selective_scan_ref identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · ba7b868fec181b57 · report

Tasks

Language ModelingLanguage ModellingMambaState Space Models

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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