← Back to all news
arXiv AI By Minghan Jiang, Jiayi Wang, Shuaiting Li, Haibin Shen, Kejie Huang

DynaTE: Accelerating Diffusion LLMs via Dynamic Token Execution

Read the original on arXiv AI →

DynaTE is a hardware–software co‑design that accelerates diffusion‑based large language models (dLLMs) by dynamically adapting execution to token states. It skips low‑utility token computations, uses a dimension‑reconfigurable processing array, refines locally dependent tokens with FLDD, and streams vocabulary to handle irregular token patterns. These techniques yield 2.05–2.78× speedup and 2.99–3.93× higher energy efficiency compared to existing dLLM accelerators, and outperform Jetson AGX Orin by 2.55× speedup and 6.07× energy efficiency.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computation and Language
Sep 23

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Flash-dLLM is a training‑free inference acceleration framework that improves the speed and memory efficiency of Diffusion Large Language Models (dLLMs). It tackles GPU memory I/O bottlenecks by introducing an I/O‑aware fused KV‑cache kernel and then employs a draft‑and‑verify decoding strategy that uses the dLLM itself as both drafter and verifier. Experiments on mathematical reasoning and code‑generation tasks show Flash‑dLLM outperforms existing acceleration methods, achieving up to 11.0× speedups over the Elastic‑Cache baseline.

By Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen
llmsdiffusionefficiencybenchmarks
More like this →
arXiv Machine Learning
Jun 26

Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM

arXiv:2606. 26120v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms.

By Tianyi Wu, Xiaoxi Sun, Yanhua Jiao, Yulin Li, Yixin Chen, YunHao Cao, YiQi Hu, Zhuotao Tian
llmsdiffusionefficiencybenchmarks
More like this →
arXiv Machine Learning
Jul 14

FastTPS: An Optimized Method for LLM Token Phase for AI accelerators

arXiv:2607. 11211v1 Announce Type: new Abstract: The popularity of large language models (LLMs) escalates an ongoing demand for effective inference.

By Wenzong Yang, Danyang Zhang, Kun Cao, Tejus Siddagangaiah, Rajeev Patwari, Zhanxing Pu, Siyin Kong, Zijiang Yang, Hao Zhu, Varun Sharma, Yue Gao, Tianping Li, Fan Yang, Jicheng Chen, Yushan Chen, Fennian Zhao, Aaron Ng, Elliott Delaye, Ashish Sirasao, Sudip Nag
llmsefficiency
More like this →