Papers › Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence

26 Mar 2025arXiv:2503.20533archive 2025-07-28

Yijiong Yu

Recent advances in reasoning models have demonstrated significant improvements in accuracy, particularly for complex tasks such as mathematical reasoning, by employing detailed and comprehensive reasoning processes. However, generating these lengthy reasoning sequences is computationally expensive and time-consuming. To address this inefficiency, we leverage the inherent parallelizability of certain tasks to accelerate the reasoning process. Specifically, when multiple parallel reasoning branches exist, we decode multiple tokens per step using a specialized attention mask, processing them within a single sequence. Experimental results show that our method achieves over 100% speedup in decoding time while basically maintaining accuracy.

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 13 code samples: 10 from 1 repository linked to this paper, 3 identical to code harvested from another paper's repository. Across all 13: 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 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: 10 samples from 1 repository, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed); 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.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 9 samples that ran have no recorded date.

yuyijiong/parallel-decoding-in-one-sequence officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 6 ran (1 instrument-failed) · 4 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: 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 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 · our draft was wrong
2ran; the contract check could not run
5ran
4unverified

Licence: 13 of the 13 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 yuyijiong/parallel-decoding-in-one-sequence. 3 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.

yuyijiong/parallel-decoding-in-one-sequence official repository 10 samples, 6 ran (1 instrument-failed) · 4 unverified
Qwen2Attention modeling_qwen2.py ran · metamorphic tier: deterministic no licence file found · pointer only · bb3e5ab4d14134fa · report fixture: returned Qwen2Attention · level recorded 2026-09-22
Qwen2MLP modeling_qwen2.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 0b7204a99a29e9f0 · report fixture: returned Qwen2MLP · level recorded 2026-09-22
Qwen2PreTrainedModel modeling_qwen2.py ran · metamorphic tier: deterministic no licence file found · pointer only · 6641879fc0a39433 · report fixture: returned Qwen2PreTrainedModel · level recorded 2026-09-22
Qwen2RMSNorm modeling_qwen2.py ran · metamorphic tier: deterministic no licence file found · pointer only · ea8879988dece177 · report fixture: returned Qwen2RMSNorm · level recorded 2026-09-22
Qwen2RotaryEmbedding modeling_qwen2.py ran · metamorphic tier: deterministic no licence file found · pointer only · f3c1b1406deb4ad1 · report fixture: returned Qwen2RotaryEmbedding · level recorded 2026-09-22
_prepare_4d_causal_attention_mask_with_cache_position modeling_qwen2.py ran · our draft was wrong no licence file found · pointer only · a73c20a30e591545 · report fixture: signature attention_mask:Tensor/2/float, sequence_length:int/0/int, target_length:int/0/int, dtype:dtype/0/?, device:device/0/?, min_dtype:float/0/float, cache_position:Tensor/1/int, batch_size:int/0/int · returned Tensor · level recorded 2026-09-22
Qwen2DecoderLayer modeling_qwen2.py unverified no licence file found · pointer only · 3fcec7a2529f7ff3 · report
Qwen2FlashAttention2 modeling_qwen2.py unverified no licence file found · pointer only · be6ea9cb7fa07851 · report
Qwen2ParaModel modeling_qwen2.py unverified no licence file found · pointer only · 252125a25cb155ce · report
Qwen2SdpaAttention modeling_qwen2.py unverified no licence file found · pointer only · c9686309ac575131 · report
Repository not located 3 samples, 3 ran (3 instrument-failed) · 0 unverified
3 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
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · 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
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 Parallel Decoding within One Sequence (graph method: Parallel Decoding within One Sequence). 13 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. Qwen2ParaModel entry · level 0 · unverified · 252125a25cb155ce
  2. Qwen2DecoderLayer model · level 0 · unverified · 3fcec7a2529f7ff3
  3. Qwen2PreTrainedModel helper · level 1 · ran · 6641879fc0a39433
  4. Qwen2RMSNorm helper · level 1 · ran · ea8879988dece177
  5. _prepare_4d_causal_attention_mask_with_cache_position helper · level 1 · ran · our draft was wrong · a73c20a30e591545
  6. Qwen2MLP model · level 1 · ran · 0b7204a99a29e9f0
  7. Qwen2Attention model · level 1 · ran · bb3e5ab4d14134fa
  8. Qwen2FlashAttention2 model · level 0 · unverified · be6ea9cb7fa07851
  9. Qwen2RotaryEmbedding helper · level 1 · ran · f3c1b1406deb4ad1
  10. Qwen2SdpaAttention model · level 0 · unverified · c9686309ac575131
  11. apply_rotary_pos_emb helper · level 1 · ran; the contract check could not run (RAISES) · 0fe82a947dc39b42
  12. repeat_kv helper · level 2 · ran; the contract check could not run (RAISES) · 3c76e52815c5401d
  13. rotate_half helper · level 1 · ran · our draft was wrong · e03d53ba9d4f9ae5

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="2503.20533") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Mathematical Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionSoftmax

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