SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.20533 · EMNLP · 2025

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence

Wei Wang, Yijiong Yu, Ji Pei

arXiv · PDF · Open in the Atlas

Code that ran

9 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 4 failures of our instrument; 4 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2503.20533.json · badge: /api/ran/2503.20533.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
yuyijiong/parallel-decoding-in-one-sequence marked official in Papers with Code
Papers with Code archive
6 ran · 4 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
FunctionStatusWhere it lives
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from Time-MoE/Time-MoE
pointer only · get_code("3c76e52815c5401d")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Qwen2Attention Ran
ran on a synthesized input · constructed an object; no result was computed
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("bb3e5ab4d14134fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Qwen2MLP Ran
ran on a synthesized input · constructed an object; no result was computed
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("0b7204a99a29e9f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Qwen2PreTrainedModel Ran
ran on a synthesized input · constructed an object; no result was computed
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("6641879fc0a39433")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Qwen2RMSNorm Ran
ran on a synthesized input · constructed an object; no result was computed
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("ea8879988dece177")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Qwen2RotaryEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("f3c1b1406deb4ad1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_prepare_4d_causal_attention_mask_with_cache_position Ran
ran; our contract draft was wrong, not the code
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("a73c20a30e591545")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from jlamprou/Infini-Attention
pointer only; the stored copy get_code serves, from jlamprou/Infini-Attention, is pointer only (licence: NONE) · get_code("0fe82a947dc39b42")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rotate_half Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from Time-MoE/Time-MoE
pointer only · get_code("e03d53ba9d4f9ae5")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Qwen2DecoderLayer Not yet run
unverified (harvested, no recorded run)
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("3fcec7a2529f7ff3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Qwen2FlashAttention2 Not yet run
unverified (harvested, no recorded run)
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("be6ea9cb7fa07851")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Qwen2ParaModel Not yet run
unverified (harvested, no recorded run)
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("252125a25cb155ce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Qwen2SdpaAttention Not yet run
unverified (harvested, no recorded run)
yuyijiong/parallel-decoding-in-one-sequence/modeling_qwen2.py
pointer only (licence: NONE) · get_code("c9686309ac575131")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuyijiong/parallel-decoding-in-one-sequence when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 4 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
rotate_half
brick of this paper's assembly: helper
360 other papers
250 dated earlier, 14 the same month, 88 later, 5 same year, order not determinable, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
repeat_kv
brick of this paper's assembly: helper
243 other papers
167 dated earlier, 10 the same month, 60 later, 4 same year, order not determinable, 2 undated · 22 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
and 240 more not named here
apply_rotary_pos_emb
brick of this paper's assembly: helper
75 other papers
58 dated earlier, 2 the same month, 14 later, 1 same year, order not determinable · 2 only as an assembly brick
2309.11499 (2023-09)
DreamLLM: Synergistic Multimodal Comprehension and Creation
2312.02051 (2023-12)
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
2312.03414 (2023-12)
Compressed Context Memory For Online Language Model Interaction
and 72 more not named here
Qwen2RMSNorm
brick of this paper's assembly: helper
1 other paper
1 later
2505.22038 (2025-05)
Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization
_prepare_4d_causal_attention_mask_with_cache_position
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2410.03115 (2024-10)
X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent advances in reasoning models have demonstrated significant improvements in accuracy 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 steps exist, we decode multiple tokens per forward pass via a tree-like attention mask within a single sequence, avoiding additional memory usage. Experimental results show that our method achieves up to nearly 100% speedup in decoding while basically maintaining the answer quality. Our code is available in https://github.com/yuyijiong/paralleldecoding-in-one-sequence.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2503.20533")
get_code_for_paper("2503.20533")
have("2503.20533")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2503.20533.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2503.20533.svg)](https://syntology.ai/paper/2503.20533)

Connect an agent — have() is free.