D3D：异步投机解码框架，Qwen3-8B 上实现 5 倍加速
D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding
复旦团队新出的 D3D，让扩散草稿不用等目标模型的隐藏状态，解码比 DFlash 快一截，GSM8K 上能到 7.48 倍，做推理加速的可以看看。
复旦大学团队发布 D3D，一种独立的扩散草稿模型，去除了草稿生成与目标模型隐藏状态之间的依赖，使草稿和验证可以异步并行。在以 Qwen3-8B 为目标模型的测试中，从 36 层剪掉 5 层仍保留超过 99% 的平均接受长度。跨 7 个基准测试，D3D 以 Qwen3-8B 和 Qwen3-32B 为目标分别取得 5.00 倍和 5.71 倍解码加速，对比 DFlash 的 4.03 倍和 3.67 倍。在 GSM8K 基准上以 Qwen3-32B 为目标时，加速达到 7.48 倍。代码已在 GitHub 开源。
D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding
Target-conditioned diffusion drafters predict candidate tokens in parallel, yet each new block must wait for updated target-model hidden states. This forces drafting and verification to run sequentially, limiting speedup even though each block is generated in one pass. We introduce D3D, a standalone diffusion drafter that removes this inter-round dependency. D3D combines blockwise denoising with auxiliary autoregressive supervision to achieve long accepted prefixes without target hidden states. This independence lets D3D draft successor blocks during verification in one packed pass, enabling asynchronous speculative decoding. We progressively prune layers according to their effect on acceptance length to reduce the cost of packed drafting. Removing five of 36 layers retains over 99\% of mean acceptance length across three benchmarks with Qwen3-8B as the target. Across seven benchmarks, D3D averages 5.00$\times$ and 5.71$\times$ decoding speedup with Qwen3-8B and Qwen3-32B targets, compared with 4.03$\times$ and 3.67$\times$ for DFlash. On GSM8K with Qwen3-32B, speedup reaches 7.48$\times$. Code is publicly available at https://github.com/fudan-generative-vision/D3D.