DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference

• URL: http://arxiv.org/abs/2604.15750v1
• Date: Fri, 17 Apr 2026 06:53:27 GMT
• Title: DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference
• Abstract summary: Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive language generation.<n>To unlock this potential, DLM inference must carefully balance generation quality and decoding speed.<n>We propose DepCap, a training-free framework for efficient block-wise DLM inference.
• Score: 16.909416809565194
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive language generation due to their potential for parallel decoding and global refinement of the entire sequence. To unlock this potential, DLM inference must carefully balance generation quality and decoding speed. Recent block-wise DLM decoding methods improve this trade-off by performing diffusion-based decoding sequentially in blocks. However, existing methods typically rely on fixed block schedules or current-step local signals to determine block boundaries, and use conservative confidence-based parallel decoding to avoid conflicts, limiting the quality-speed trade-off. In this paper, we argue that block-wise DLM inference requires more suitable signals for its two core decisions: cross-step signals for determining block boundaries, and token-level conflict signals for parallel decoding. Based on this view, we propose DepCap, a training-free framework for efficient block-wise DLM inference. Specifically, DepCap instantiates the cross-step signal as the influence of the last decoded block and uses it to adaptively determine how far the next block should extend, while identifying a conflict-free subset of tokens for safe parallel decoding within each block, enabling substantial inference acceleration with negligible quality degradation. DepCap is a plug-and-play method applicable to various DLMs, and compatible with existing KV-cache strategies for block-wise DLM. An information-theoretic analysis further suggests that the cumulative last-block influence on a candidate block is approximately additive across tokens, supporting the proposed block-partitioning criterion. Experimental results show that DepCap achieves favorable speed-quality trade-offs across multiple DLM backbones and reasoning and coding benchmarks, with up to 5.63$\times$ speedup without significant performance degradation.

Related papers

• BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding [20.29443489871258]
  Speculative decoding improves parallelism by generating multiple tokens per forward pass via block-level diffusion.<n>Existing methods adopt a fixed inference block size and assume a uniform optimal decoding strategy across all inputs.<n>We show that this assumption is suboptimal, as the optimal block size varies across samples and plays a critical role in speculative decoding performance.<n>We propose BlockPilot, a sample-adaptive policy that predicts the optimal block size from the prefilling representation.
  arXiv  Detail & Related papers  (2026-06-30T08:24:05Z)
• 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)
• Prefix-Adaptive Block Diffusion for Efficient Document Recognition [52.15352911463151]
  Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsing.<n>We propose the Prefix- Block Diffusion Model (PA-BDM) which replaces intra-block bidirectional denoising with causal denoising from prefix to suffix.<n> Experiments show that the 3B PA-BDM achieves higher recognition scores on several benchmarks and improves inference throughput by 71.6% over the 2.5B MinerU-Diffusion.
  arXiv  Detail & Related papers  (2026-05-16T07:50:13Z)
• Advancing Block Diffusion Language Models for Test-Time Scaling [73.54022593833638]
  We propose a unified framework for test-time scaling in BDLMs.<n>We introduce adaptivity in both decoding and block-wise generation.<n>We show that applying BACD and TCCF to TDAR-8B yields significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-02-10T09:05:07Z)
• DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs [17.284485483927448]
  Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation.<n>The widely-used fixed, predefined block (naive) schedule is agnostic to semantic difficulty, making it a suboptimal strategy for both quality and efficiency.<n>We propose Dynamic Sliding Block (DSB), a training-free block scheduling method that uses a sliding block with a dynamic size to overcome the rigidity of the naive block.
  arXiv  Detail & Related papers  (2026-02-05T18:41:38Z)
• Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models [40.39823804602205]
  Swordsman is an entropy-driven adaptive block-wise decoding framework for diffusion language models.<n>It partitions blocks by identifying entropy shifts between adjacent tokens to better align with semantic or syntactic constituent boundaries.<n>As a training-free framework, Swordsman demonstrates state-of-the-art performance across extensive evaluations.
  arXiv  Detail & Related papers  (2026-02-04T10:27:49Z)
• WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference [44.87788417755154]
  We propose WeDLM, a diffusion decoding framework built entirely on standard causal attention.<n>We show that WeDLM preserves the quality of strong AR backbones while delivering substantial speedups.
  arXiv  Detail & Related papers  (2025-12-28T01:25:48Z)
• From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs [58.640039233470766]
  We show that principled AR-to-block-diffusion adaptation is an effective and compute-efficient alternative to training DLMs from scratch.<n> NBDiff-7B (Base and Instruct) could inherit the long-context modeling and reasoning capabilities, and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-07T10:28:21Z)
• AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size [7.442463267121892]
  Diffusion-based large language models (dLLMs) are gaining attention for their inherent capacity for parallel decoding.<n>This paper presents the first systematic investigation challenging the fixed block size assumption in semi-AR decoding.<n>We introduce AdaBlock-dLLM, a training-free, plug-and-play scheduler that adaptively aligns block boundaries with semantic steps by adjusting block size during runtime.
  arXiv  Detail & Related papers  (2025-09-30T15:53:56Z)
• Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding [60.06816407728172]
  Discrete diffusion language models have shown strong potential for text generation.<n>Standard supervised fine-tuning misaligns with semi-autoregressive inference.<n>We propose Blockwise SFT, which partitions responses into fixed-size blocks.
  arXiv  Detail & Related papers  (2025-08-27T02:49:33Z)
• 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)

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.