Papers › TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

7 Oct 2024arXiv:2410.05076archive 2025-07-28

Lijie Yang, Zhihao Zhang, Zhuofu Chen, Zikun Li, Zhihao Jia

Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the expanding key-value (KV) cache size required by Transformer architectures intensifies the memory constraints, particularly during the decoding phase, creating a significant bottleneck. Existing sparse attention mechanisms designed to address this bottleneck have two limitations: (1) they often fail to reliably identify the most relevant tokens for attention, and (2) they overlook the spatial coherence of token selection across consecutive Transformer layers, which can lead to performance degradation and substantial overhead in token selection. This paper introduces TidalDecode, a simple yet effective algorithm and system for fast and accurate LLM decoding through position persistent sparse attention. TidalDecode leverages the spatial coherence of tokens selected by existing sparse attention methods and introduces a few token selection layers that perform full attention to identify the tokens with the highest attention scores, while all other layers perform sparse attention with the pre-selected tokens. This design enables TidalDecode to substantially reduce the overhead of token selection for sparse attention without sacrificing the quality of the generated results. Evaluation on a diverse set of LLMs and tasks shows that TidalDecode closely matches the generative performance of full attention methods while reducing the LLM decoding latency by up to 2.1x.

PaperPDFCodeCode Syntology ran

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 13 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 12 ran (3 with no instrument failure; 9 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 6 of the 12 samples that ran have no recorded date.

DerrickYLJ/TidalDecode officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 13 samples, 12 ran (9 instrument-failed) · 1 unverified 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: 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 9 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
7ran · our draft was wrong
2ran; the contract check could not run
1ran
1unverified

Licence: 4 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from DerrickYLJ/TidalDecode. “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”. “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.

DerrickYLJ/TidalDecode official repository 13 samples, 12 ran (9 instrument-failed) · 1 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
src/models/llama_tidaldecoding.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (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
src/models/llama_tidaldecoding.py ran · our draft was wrong Apache-2.0 (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
build_chat in 29 papers experiments/LongBench/pred.py ran Apache-2.0 (permissive) · 1707cb62894075a9 · report fixture: signature tokenizer:StandInTokenizer/0/?, prompt:str/0/str, model_name:str/0/str · returned str · level recorded 2026-09-24
count_score in 27 papers experiments/LongBench/metrics.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · b349b79d9cc2934b · report fixture: signature prediction:str/0/str, ground_truth:int/0/int · returned float · level recorded, date not recorded
download_url in 32 papers src/utils.py ran · our draft was wrong Apache-2.0 (permissive) · d196dde52e17237c · report fixture: signature url:str/0/str, folder:str/0/str · returned str · level recorded 2026-09-24
load_jsonl in 179 papers src/utils.py ran · our draft was wrong Apache-2.0 (permissive) · a8b4a0de765a348c · report fixture: signature file_path:str/0/str · returned list · level recorded 2026-09-24
normalize_answer in 304 papers experiments/LongBench/metrics.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · e7e75981cb464788 · report fixture: signature s:str/0/str · returned str · level recorded, date not recorded
normalize_zh_answer in 32 papers experiments/LongBench/metrics.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 8c5c581f9264c810 · report fixture: signature s:str/0/str · returned str · level recorded, date not recorded
post_process in 56 papers experiments/LongBench/pred.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 4489113b536ca6eb · report fixture: signature response:str/0/str, model_name:str/0/str · returned str · level recorded 2026-09-22
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input
src/models/yarn_tidaldecoding.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 53b2e52873fb8342 · report fixture: returned Tensor · level recorded 2026-09-24
rmsnorm_func in 9 papers src/models/yarn_tidaldecoding.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · ab6fba34dd3815d7 · report fixture: signature hidden_states:Tensor/2/float, weight:Tensor/1/float, variance_epsilon:float/0/float · returned Tensor · level recorded 2026-09-26
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
src/models/llama_tidaldecoding.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b99eea6376d1e212 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
parse_args in 355 papers experiments/LongBench/pred.py unverified Apache-2.0 (permissive) · dc041ea24b9ceb27 · report

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 ConnectionSETSoftmaxTransformer

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