arXiv:2608. 06628v1 Announce Type: new Abstract: Diffusion language models (dLLMs) offer a promising alternative to autoregressive models by accelerating inference through parallel decoding.
By Jinha Kim, Younghun Roh, Jaeyeon Kim
Step-dLLM introduces an adaptive, step-aware sparse attention mechanism for diffusion large language models (dLLMs). It refreshes a block-sparse mask at specific anchor steps along the denoising trajectory and applies a head-adaptive global sparsity budget, allowing efficient reuse of attention patterns within locally consistent intervals. The method, implemented with a fused IO-aware Triton kernel, achieves a 2.78× speedup over dense FlashAttention on LLaDA-1.5 while improving the accuracy‑latency trade‑off compared to prior sparse‑attention approaches.
By Zhichen Zeng, Xichong Zhang, Junpan Wu, Yifei Zuo, Chi-Chih Chang, Jiayi Wang, Maohua Nie, Ji Liu, Ang Li, Banghua Zhu
arXiv:2602. 14209v2 Announce Type: replace Abstract: Block diffusion LLMs are an emerging paradigm for parallel language generation, but their KV caching makes memory access the dominant bottleneck in long-context inference.
By Omin Kwon, Yeonjae Kim, Doyeon Kim, Minseo Kim, Yeonhong Park, Jae W. Lee
The paper introduces a training‑free structured suffix modeling technique to accelerate Diffusion Language Models (DLMs). It partitions the suffix into local, middle, and tail regions, retaining varying numbers of tokens per region and incorporating previous decoding results into current token representations. Experiments on three DLMs show significant speedups—up to 72.81× in long‑sequence inference—while often improving performance, and the method is compatible with existing acceleration strategies.
By Zifeng Cheng, Keda Li, Zhiwei Jiang, Cong Wang, Fei Shen, Qing Gu
arXiv:2605. 29233v2 Announce Type: replace-cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decoding.
By Xiaoyou Wu, Cheng-Jhih Shih, Binfei Ji, Yong Liu, Yingyan Celine Lin
Prefilling-dLLM v2 is a diffusion language model that learns to route computation using a native mask token, enabling efficient sparse attention across long contexts. By appending a mask at the end of each chunk and using a learned role offset, the model selectively attends to top‑K chunks every fourth layer while maintaining local windows elsewhere. Evaluated on 16K–128K contexts, Prefilling-dLLM v2 outperforms other sparse methods (NSA, DSA, SWA) on RULER tasks and achieves a 172× speedup over full dense attention at 128K tokens.
arXiv:2606.10537v2 Announce Type: replace
Abstract: Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales
quadratically with...
By Jing Xiong, Qi Han, Shansan Gong, Yunta Hsieh, Boyuan Zheng, Chengyue Wu, Chaofan Tao, Chenyang Zhao, Ngai Wong
Diffusion Language Models (DLMs) exhibit strong parallel decoding capabilities by denoising multiple tokens in a single generation step. However, this parallelism comes with substantial computational...
arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.
By Zhiyuan Liu, Yicun Yang, Yaojie Zhang, Junjie Chen, Chang Zou, Qingyuan Wei, Shaobo Wang, Yichen Zhu, Linfeng Zhang
arXiv:2601. 17917v3 Announce Type: replace 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.
By Zhongyu Xiao, Zhiwei Hao, Jianyuan Guo, Yong Luo, Jia Liu, Jie Xu, Han Hu
Split-KV introduces a context‑parallelism technique for training diffusion drafters, keeping key/value shards local and limiting per‑layer attention communication to query‑sized tensors. This approach exploits the asymmetry between short draft queries and long contexts, enabling efficient load balancing via a cost‑aware longest‑processing‑time‑first strategy. Experiments show that at a CP size of 64, Split‑KV achieves 85–91 % weak‑scaling efficiency and up to 3.67× speedup over the best baseline, with less than 1 % load imbalance.
By Geng Zhang, Fangzhao Zhang, Cong Xie, Tiantian Fan, Yang You
arXiv:2601. 03043v4 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency.
By Junhao Hu, Fangze Li, Mingtao Xu, Feifan Meng, Shiju Zhao, Tiancheng Hu, Ting Peng, Anmin Liu, Wenrui Huang, Chenxu Liu, Ziyue Hua, Tao Xie