treaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding

• URL: http://arxiv.org/abs/2601.17917v1
• Date: Sun, 25 Jan 2026 17:36:04 GMT
• Title: treaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding
• Authors: Zhongyu Xiao, Zhiwei Hao, Jianyuan Guo, Yong Luo, Jia Liu, Jie Xu, Han Hu,
• Abstract summary: Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation.<n>Recent works have accelerated inference via KV cache reuse or decoding, but overlook the intrinsic inefficiencies within the block-wise diffusion process.<n>We propose Streaming-dLLM, a training-free framework that streamlines inference across both spatial and temporal dimensions.
• Score: 36.74241893088594
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While recent works have accelerated inference via KV cache reuse or heuristic decoding, they overlook the intrinsic inefficiencies within the block-wise diffusion process. Specifically, they suffer from spatial redundancy by modeling informative-sparse suffix regions uniformly and temporal inefficiency by applying fixed denoising schedules across all the decoding process. To address this, we propose Streaming-dLLM, a training-free framework that streamlines inference across both spatial and temporal dimensions. Spatially, we introduce attenuation guided suffix modeling to approximate the full context by pruning redundant mask tokens. Temporally, we employ a dynamic confidence aware strategy with an early exit mechanism, allowing the model to skip unnecessary iterations for converged tokens. Extensive experiments show that Streaming-dLLM achieves up to 68.2X speedup while maintaining generation quality, highlighting its effectiveness in diffusion decoding. The code is available at https://github.com/xiaoshideta/Streaming-dLLM.

Related papers

• Causal Autoregressive Diffusion Language Model [70.7353007255797]
  CARD reformulates the diffusion process within a strictly causal attention mask, enabling dense, per-token supervision in a single forward pass.<n>Our results demonstrate that CARD achieves ARM-level data efficiency while unlocking the latency benefits of parallel generation.
  arXiv  Detail & Related papers  (2026-01-29T17:38:29Z)
• VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding [52.69880888587866]
  VidDA is a Video LLM based on the Diffusion Language Model.<n>We introduce MARS-Cache to tackle the bottleneck inference of diffusion decoding on massive video tokens.<n>Experiments show VidDA outperforms diffusion baselines and rivals state-of-the-art autoregressive models.
  arXiv  Detail & Related papers  (2026-01-25T15:02:01Z)
• 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)
• Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model [98.35868970993232]
  Diffusion language models (DLMs) are emerging as a powerful and promising alternative to the dominant autoregressive paradigm.<n>We introduce efficient Sampling with Adaptive acceleration and Backtracking Enhanced Remasking (i.e., Saber) to achieve better inference speed and output quality in code generation.
  arXiv  Detail & Related papers  (2025-10-20T23:38:12Z)
• Fast-dLLM v2: Efficient Block-Diffusion LLM [64.38006546510337]
  Fast-dLLM v2 is a block diffusion language model that adapts pretrained AR models into dLLMs for parallel text generation.<n>This represents a 500x reduction in training data compared to full-attention diffusion LLMs such as Dream (580B tokens)
  arXiv  Detail & Related papers  (2025-09-30T14:40:18Z)
• Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning [23.58934174168992]
  Autoregressive (AR) language models generate text one token at a time, which limits their inference speed.<n>We propose Convolutional decoding (Conv), a normalization-based method that narrows the decoding window without hard segmentation.<n>We also introduce Rejecting Rule-based Fine-Tuning (R2FT), a post-hoc training scheme that better aligns tokens at positions far from context.
  arXiv  Detail & Related papers  (2025-09-18T17:48:21Z)
• Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction [72.27673320976933]
  Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding.<n>Current caching techniques accelerate decoding by storing full-layer states, yet impose substantial memory usage.<n>We propose Sparse-dLLM, the first training-free framework integrating dynamic cache eviction with sparse attention.
  arXiv  Detail & Related papers  (2025-08-04T16:14:03Z)
• 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)
• FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion [22.207275433870937]
  Diffusion language models offer parallel token generation and inherent bidirectionality.<n>State-of-the-art diffusion models (e.g., Dream 7B, LLaDA 8B) suffer from slow inference.<n>We introduce Guided Diffusion, a training-free method that uses a lightweight pretrained autoregressive model to supervise token unmasking.
  arXiv  Detail & Related papers  (2025-05-27T17:39:39Z)

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.