动态调整生成块大小，提升扩散语言模型的生成质量和速度。
DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs
- 用可变大小滑动块替代固定块，根据语义难度自适应调度。
- 在多个模型和基准上实现更优的生成质量与推理效率。
- 无需训练，适合追求高效高质文本生成的研究与开发者。
扩散大语言模型（dLLMs）作为文本生成的新范式，天然支持并行解码。实际应用中，块推理对避免全局双向解码中的顺序错位、提升输出质量至关重要。然而，广泛采用的固定预设块（朴素）调度策略忽视语义难度，导致在不确定性高的位置过早确定内容，同时延迟靠近块边界的简单位置。本文分析了朴素调度的局限性，揭示了根据语义难度动态调整调度对可靠高效推理的重要性。为此，提出无需训练的动态滑动块（DSB）方法，通过可变大小的滑动块克服传统块的僵化问题。为进一步提升效率，引入适配DSB的训练免费KV缓存机制DSB Cache。在多个模型与基准上的大量实验表明，DSB结合DSB Cache能持续提升dLLMs的生成质量与推理效率。代码已公开于https://github.com/lizhuo-luo/DSB。
原文摘要 · Abstract (English)
Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block inference is crucial for avoiding order misalignment in global bidirectional decoding and improving output quality. However, the widely-used fixed, predefined block (naive) schedule is agnostic to semantic difficulty, making it a suboptimal strategy for both quality and efficiency: it can force premature commitments to uncertain positions while delaying easy positions near block boundaries. In this work, we analyze the limitations of naive block scheduling and disclose the importance of dynamically adapting the schedule to semantic difficulty for reliable and efficient inference. Motivated by this, 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. To further improve efficiency, we introduce DSB Cache, a training-free KV-cache mechanism tailored to DSB. Extensive experiments across multiple models and benchmarks demonstrate that DSB, together with DSB Cache, consistently improves both generation quality and inference efficiency for dLLMs. Code is released at https://github.com/lizhuo-luo/DSB.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。