Papers › Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

10 Apr 2024arXiv:2404.07143archive 2025-07-28

Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth Gopal

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed Infini-attention. The Infini-attention incorporates a compressive memory into the vanilla attention mechanism and builds in both masked local attention and long-term linear attention mechanisms in a single Transformer block. We demonstrate the effectiveness of our approach on long-context language modeling benchmarks, 1M sequence length passkey context block retrieval and 500K length book summarization tasks with 1B and 8B LLMs. Our approach introduces minimal bounded memory parameters and enables fast streaming inference for LLMs.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples: 12 from 4 repositories linked to this paper, 4 identical to code harvested from another paper's repository. Across all 16: 15 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 4 repositories, 11 ran (5 with no instrument failure; 6 where Syntology's instrument failed); 4 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 7 of the 15 samples that ran have no recorded date.

ArionDas/InfiniGPT mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
Beomi/InfiniTransformer mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (3 instrument-failed) · 0 unverified report
jlamprou/Infini-Attention mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
lucidrains/infini-transformer-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
mustafaaljadery/gemma-2b-10m mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

16 samples harvested: 15 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · violated contract
4ran · our draft was wrong
4ran; the contract check could not run
5ran
1unverified

Licence: 6 of the 16 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 4 samples are listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ArionDas/InfiniGPT community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
CompressiveMemory src/infini_transformer.py ran Apache-2.0 (permissive) · e3e97263839cab4f · report fixture: returned CompressiveMemory · level recorded 2026-09-22
FeedForward in 198 papers src/infini_transformer.py ran fingerprinted Apache-2.0 (permissive) · 6190672bce0e4f2a · report fixture: returned FeedForward · level recorded 2026-09-22
GELU in 21 papers src/infini_transformer.py ran fingerprinted Apache-2.0 (permissive) · 9fa049dcf996a066 · report fixture: returned GELU · level recorded 2026-09-22
PositionEmbeddings src/infini_transformer.py ran Apache-2.0 (permissive) · a4a13041dd37b6f2 · report fixture: returned PositionEmbeddings · level recorded 2026-09-22
InfiniTransformer src/infini_transformer.py unverified Apache-2.0 (permissive) · e59592481467fbed · report
Beomi/InfiniTransformer community (archive-listed) 4 samples, 4 ran (3 instrument-failed) · 0 unverified
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
modeling_gemma.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 30d7eec482ebf6b1 · report fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded, date not recorded
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
modeling_gemma.py ran · our draft was wrong MIT (permissive) · bac65c3dafaec040 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, cos:Tensor/3/float, sin:Tensor/3/float, position_ids:NoneType/0/?, unsqueeze_dim:int/0/int · returned tuple · level recorded, date not recorded
get_mem_space in 8 papers gpu_mem_track.py ran MIT (permissive) · a01911ff65691be7 · report fixture: signature x:dtype/0/? · returned float · level recorded 2026-09-24
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
modeling_gemma.py ran · our draft was wrong fingerprinted MIT (permissive) · b99eea6376d1e212 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
jlamprou/Infini-Attention community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
infiniAttention.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 0fe82a947dc39b42 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, cos:Tensor/2/float, sin:Tensor/2/float, position_ids:Tensor/2/int, unsqueeze_dim:int/0/int · returned tuple · level recorded 2026-09-22
generate_prompt_landmark in 8 papers passkey_retrieval.py ran · our draft was wrong no licence file found · pointer only · 943aef7d2bbc32d0 · report fixture: signature n_garbage:int/0/int, seed:int/0/int · returned tuple · level recorded 2026-09-22
lucidrains/infini-transformer-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
retrieve_from_kv_memories infini_transformer_pytorch/infini_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 8d5b5a4c9c8d7db0 · report fixture: signature t:Tensor/4/float, past_memories:Memories/1/Tensor, eps:float/0/float · returned Tensor · level recorded 2026-09-22
Repository not located 4 samples, 4 ran (2 instrument-failed) · 0 unverified
4 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence of this copy not recorded · 3c76e52815c5401d · report fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded, date not recorded
default in 430 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 99b3563ebc6734ad · report fixture: signature v:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input
repository not located ran · violated contract fingerprinted licence of this copy not recorded · b7c3487f192e31b7 · report fixture: signature v:int/0/int · returned bool · level recorded, date not recorded
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · e03d53ba9d4f9ae5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Infini-attention (graph method: Infini-attention). 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. InfiniTransformer entry · level 0 · unverified · e59592481467fbed
  2. CompressiveMemory model · level 1 · ran · e3e97263839cab4f
  3. FeedForward model · level 1 · ran · 6190672bce0e4f2a
  4. PositionEmbeddings helper · level 1 · ran · a4a13041dd37b6f2
  5. GELU helper · level 1 · ran · 9fa049dcf996a066

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2404.07143") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingRetrieval

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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