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

Researchers proposed Dynamic-dLLM, a training-free framework to accelerate Diffusion Large Language Models (dLLMs) by dynamically allocating cache budgets and calibrating decoding thresholds. The method achieves over 3x speedup on models like LLaDA-8B-Instruct and Dream-v0-7B-Instruct without performance loss, addressing computational challenges in long-sequence and real-time applications.

arXiv:2606.26120v1 Announce Type: new Abstract: Diffusion Large Language Models dLLMs offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms. However, their computational complexity scales on the order of L cubed with the sequence length L. This poses significant challenges for long-sequence and real-time applications, primarily due to the lack of compatibility with key-value caching and the non-autoregressive nature of denoising steps. Existing acceleration methods rely on static caching or parallel decoding strategies, which fail to account for the dynamic behavior of token properties across layers and decoding steps. We propose Dynamic-dLLM, a training-free framework that enhances dLLM inference efficiency through two components: Dynamic Cache Updating DCU , which adaptively allocates cache-update budgets based on layer-wise token dynamics, and Adaptive Parallel Decoding APD , which dynamically calibrates decoding thresholds to balance generation quality and efficiency. Extensive experiments on models like LLaDA-8B-Instruct, LLaDA-1.5, and Dream-v0-7B-Instruct across benchmarks such as MMLU, GSM8K, and HumanEval demonstrate that Dynamic-dLLM significantly improves inference speed. It attains an average speedup exceeding 3 times while maintaining performance. Dynamic-dLLM outperforms state-of-the-art acceleration methods and provides a plug-and-play solution for efficient dLLM deployment without compromising performance. The code is available at https://github.com/TianyiWu233/DYNAMIC-DLLM.