Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs

• URL: http://arxiv.org/abs/2603.12996v1
• Date: Fri, 13 Mar 2026 13:52:02 GMT
• Title: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs
• Abstract summary: Parallel decoding for diffusion LLMs is difficult because each denoising step provides only token-wise marginal distributions.<n>We propose Dependency-Aware Parallel Decoding (DAPD), a simple, training-free decoding method that uses self-attention to induce a conditional dependency graph.
• Score: 8.800270601225668
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parallel decoding for diffusion LLMs (dLLMs) is difficult because each denoising step provides only token-wise marginal distributions, while unmasking multiple tokens simultaneously requires accounting for inter-token dependencies. We propose Dependency-Aware Parallel Decoding (DAPD), a simple, training-free decoding method that uses self-attention to induce a conditional dependency graph over masked tokens. At each iteration, edges in this graph capture strong token interactions, while non-edges indicate weak dependence. Parallel decoding is then reduced to selecting an independent set on the graph and unmasking the selected tokens in parallel. This avoids co-updating strongly coupled tokens without auxiliary models or retraining. Experiments on LLaDA and Dream show that DAPD improves the accuracy-steps trade-off over existing methods and enables more globally distributed parallel updates that better exploit the any-order generation capability of dLLMs.

Related papers

• Mean-Field Parallel Decoding for Discrete Diffusion Language Models [47.086589631406035]
  We introduce a training-free decoding framework that coordinates parallel updates.<n>A variational relaxation yields a simple fixed-point update that suppresses conflicting simultaneous commitments.<n> Experiments on reasoning and code-generation benchmarks show consistent improvements in the quality-latency trade-off.
  arXiv  Detail & Related papers  (2026-06-14T13:17:58Z)
• Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models [59.51249894128724]
  Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration.<n>We propose ADAS, a training-free reranking rule for parallel masked diffusion decoding.
  arXiv  Detail & Related papers  (2026-06-09T13:17:27Z)
• SimSD: Simple Speculative Decoding in Diffusion Language Models [61.33773959352141]
  Diffusion large language models (dLLMs) offer faster inference through parallel or blockwise decoding.<n>Their masked language modeling formulation remains incompatible with standard token-level speculative decoding.<n>We propose a speculative decoding algorithm for dLLMs, named SimSD, that equips dLLMs with temporally valid token-level contexts.<n>Our method achieves up to 7.46x higher decoding throughput while maintaining and even improving average generation quality.
  arXiv  Detail & Related papers  (2026-06-01T17:46:46Z)
• PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding [32.667256256847246]
  Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences.<n>We propose Parallel Speculative Decoding (PSD), a training-free framework that jointly improves inference along both axes.
  arXiv  Detail & Related papers  (2026-05-15T04:43:02Z)
• Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models [21.699371484195865]
  We propose DEMASK, a lightweight dependency predictor that attaches to the final hidden states of a dLLM.<n> Empirically, DEMASK achieves 1.7-2.2$times$ speedup on Dream-7B while matching or improving accuracy compared to confidence-based and KL-based baselines.
  arXiv  Detail & Related papers  (2026-04-02T22:21:24Z)
• DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention [2.7422645382944935]
  We present DyLLM, a training-free inference framework that accelerates decoding by selectively computing only salient tokens.<n>Across diverse reasoning and code-generation benchmarks, DyLLM achieves up to 9.6x higher throughput.
  arXiv  Detail & Related papers  (2026-03-09T07:02:01Z)
• Divide and Conquer: Accelerating Diffusion-Based Large Language Models via Adaptive Parallel Decoding [6.755667885643806]
  Diffusion-based large language models (dLLMs) have shown promising performance across various reasoning tasks.<n>We introduce an adaptive parallel decoding approach, namely DiCo, which features a three-phase divide-and-conquer paradigm.<n>Extensive experiments demonstrate that DiCo can achieve significant inference speedups while maintaining competitive generation quality.
  arXiv  Detail & Related papers  (2026-02-27T08:36:06Z)
• DAWN: Dependency-Aware Fast Inference for Diffusion LLMs [25.499655803741103]
  Diffusion large language models (dLLMs) have shown advantages in text generation.<n>Existing inference solutions adopt conservative parallel strategies, leaving substantial efficiency potential underexplored.<n>We propose DAWN, a training-free, dependency-aware decoding method for fast dLLM inference.
  arXiv  Detail & Related papers  (2026-02-06T18:51:29Z)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [60.407727995313074]
  We introduce adaptive parallel decoding (APD), a novel method that dynamically adjusts the number of tokens sampled in parallel.<n>APD provides markedly higher throughput with minimal quality degradations on downstream benchmarks.
  arXiv  Detail & Related papers  (2025-05-31T06:10:10Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding [55.2480439325792]
  In arbitrary-order language models, it is an open question how to sample tokens in parallel from the correct joint distribution.<n>We find that a different class of models, any-subset autoregressive models (AS-ARMs), holds the solution.<n>We show that AS-ARMs achieve state-of-the-art performance among sub-200M parameter models on infilling benchmark tasks, and nearly match the performance of models 50X larger on code generation.
  arXiv  Detail & Related papers  (2025-04-29T06:33:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.