SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.08026 · ICML · 2026

DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention

Younjoo Lee, Seungkyun Dan, Junghoo Lee, Jaiyoung Park, Jung Ahn

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-21; 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/2603.08026.json · badge: /api/ran/2603.08026.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
scale-snu/DyLLM canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
tensor_parallel_cosine_mask Ran
ran; our contract draft was wrong, not the code
scale-snu/DyLLM/dyllm/distributed/parallel_state.py
code served (permissive licence) · get_code("4fd6836ef1314764")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.distributed as dist

torch.manual_seed(0)

# Create a small stats tensor with shape (batch_size, feature_dim)
# stats[..., 0:3] contains: dot product, norm_old^2, norm_new^2
# We'll create a batch of 2 with 4 features total
stats = torch.randn(2, 4, dtype=torch.float32)

# Set the first three columns to represent valid statistics
# Column 0: dot product (can be positive or negative)
stats[:, 0] = torch.tensor([0.5, -0.3], dtype=torch.float32)
# Column 1: squared L2 norm of old (positive)
stats[:, 1] = torch.tensor([2.0, 1.5], dtype=torch.float32)
# Column 2: squared L2 norm of new (positive)
stats[:, 2] = torch.tensor([1.8, 2.2], dtype=torch.float32)
# Column 3: extra feature (not used by function)
stats[:, 3] = torch.randn(2)

# Threshold for cosine similarity comparison
threshold = 0.8

ARGS = {
    "stats": stats,
    "threshold": threshold,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Masked diffusion language models enable parallel token decoding, providing a promising alternative to the sequential nature of autoregressive generation. However, their iterative denoising process remains computationally expensive because it repeatedly processes the entire sequence at every step. We observe that across these diffusion steps, most token representations remain stable; only a small subset, which we term salient tokens, contributes meaningfully to the next update. Leveraging this temporal sparsity, we present DyLLM, a training-free inference framework that accelerates decoding by selectively computing only these salient tokens. DyLLM identifies saliency by measuring the cosine similarity of attention contexts between adjacent denoising steps. It recomputes feed-forward and attention operations only for salient tokens while reusing cached activations for the remainder. Across diverse reasoning and code-generation benchmarks, DyLLM achieves up to 9.6× higher throughput while largely preserving the baseline accuracy of representative open-source diffusion LLMs, LLaDA and Dream.

For agents

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

get_harvested_code_for_paper("2603.08026")
get_code_for_paper("2603.08026")
have("2603.08026")

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

curl https://syntology.ai/api/ran/2603.08026.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.08026.svg)](https://syntology.ai/paper/2603.08026)

Connect an agent — have() is free.