Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional attention and cannot directly benefit from the standard key-value (KV) cache as autoregressive models (ARMs) do. To tackle this issue, we introduce \textit{Dual aDaptive Cache} (d$^2$Cache), which is a training-free approximate KV cache framework for accelerating dLLM inference. d$^2$Cache features a two-stage fine-grained selection strategy to identify tokens and adaptively update their KV states at each decoding step, while caching the KV states of the remaining tokens for reuse. Furthermore, d$^2$Cache naturally offers a more reliable decoding alternative, which can enable quasi left-to-right generation and mitigate premature overconfidence in tokens at the end of the sequence. Extensive experimental results on two representative dLLMs (\ie, LLaDA and Dream) demonstrate that d$^2$Cache not only achieves substantial inference speedups, but also yields consistent improvements in generation quality. The code is available at https://github.com/Kamichanw/d2Cache.

翻译：尽管基于扩散的大语言模型（dLLMs）展现出有前景的性能，但其推理效率仍然较低。这是因为dLLMs依赖于双向注意力机制，无法像自回归模型（ARMs）那样直接受益于标准的键值（KV）缓存。为解决此问题，我们提出了\textit{双重自适应缓存}（d$^2$Cache），这是一个无需训练的近似KV缓存框架，用于加速dLLM推理。d$^2$Cache采用两阶段细粒度选择策略，在每个解码步骤中识别关键令牌并自适应地更新其KV状态，同时缓存其余令牌的KV状态以供重用。此外，d$^2$Cache自然地提供了一种更可靠的解码替代方案，能够实现准从左到右的生成，并减轻对序列末端令牌的过早过度自信。在两个代表性dLLM（即LLaDA和Dream）上进行的大量实验结果表明，d$^2$Cache不仅实现了显著的推理加速，而且在生成质量上带来了一致的提升。代码可在https://github.com/Kamichanw/d2Cache获取。