D^2SD: 使用双重扩散草稿模型加速推测解码
D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models
AI总结：
提出D^2SD框架，通过双重扩散草稿模型和置信度引导的前缀树，提升推测解码的接受率，优于现有扩散方法和自回归推测解码基线。
摘要：
推测解码通过草拟多个令牌并在单次目标模型前向传递中验证它们，加速自回归大语言模型推理。最近的基于扩散的草稿模型并行生成整个令牌块，但通常每次验证只提交单个草稿序列：一旦出现第一个不匹配，所有后续草稿令牌被丢弃，导致接受率有限。简单地对更多草稿候选序列进行批处理只会带来边际改进，因为冗余或位置不当的分支增加了草拟和验证的成本，而没有成比例地增加接受的令牌数量。我们提出D^2SD，一种双重扩散草稿推测解码框架，将候选组织成置信度引导的前缀树，其中第一个扩散草稿器生成一个块以及每个位置的置信度分数，用于识别最可能的拒绝边界并选择前K个前缀范围进行恢复；第二个可变前缀扩散草稿器在每个选定前缀处重新锚定，并在一次批处理中提出替代延续；得到的共享前缀候选通过级联注意力联合验证。实验表明，D^2SD在底层扩散方法和强自回归推测解码基线上均有明显改进。
英文摘要：
Speculative decoding accelerates autoregressive large language model inference by drafting multiple tokens and verifying them in a single target-model forward pass. Recent diffusion-based drafters generate an entire block of tokens in parallel but usually commit to a single draft sequence per verification: once the first mismatch occurs, all subsequent draft tokens are discarded, resulting in a limited acceptance rate. Naively batching more draft candidate sequences only introduces a marginal improvement, as redundant or poorly placed branches increase the cost of drafting and verification without proportionally increasing the number of accepted tokens. We propose D^2SD, a dual diffusion draft speculative decoding framework that organizes candidates into a confidence-guided prefix tree, where the first diffusion drafter generates a block along with per-position confidence scores that are used to identify the most likely rejection boundary and select the top-K prefix ranges for recovery; the second variable-prefix diffusion drafter re-anchors at each selected prefix and proposes alternative continuations in one batched pass; the resulting shared-prefix candidates are jointly verified via cascade attention. Empirically, D^2SD shows clear improvements over both the underlying diffusion approach and strong autoregressive speculative decoding baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
