SJD-PAC：通过主动草稿和自适应延续加速推测性雅可比解码
SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
AI总结：
提出SJD-PAC框架，通过主动草稿策略和自适应延续机制提升推测性雅可比解码的接受率，实现无损加速文本到图像合成。
摘要：
推测性雅可比解码（SJD）提供了一种无需草稿模型的方法来加速自回归文本到图像合成。然而，视觉生成的高熵特性导致复杂区域中草稿令牌接受率低，形成严重限制整体吞吐量的瓶颈。为了克服这一问题，我们引入了SJD-PAC，一个增强的SJD框架。首先，SJD-PAC采用主动草稿策略来提高这些具有挑战性的高熵区域的局部接受率。其次，我们引入了一种自适应延续机制，在初始拒绝后维持序列验证，无需完全重新采样。这些优化协同工作，显著增加了每步的平均接受长度，在严格保持目标分布的同时提升了推理速度。在标准文本到图像基准上的实验表明，SJD-PAC实现了$3.8 imes$的加速，且图像质量无损。代码可在https://github.com/KangJialiang/SJD-PAC获取。
英文摘要：
Speculative Jacobi Decoding (SJD) offers a draft-model-free approach to accelerate autoregressive text-to-image synthesis. However, the high-entropy nature of visual generation yields low draft-token acceptance rates in complex regions, creating a bottleneck that severely limits overall throughput. To overcome this, we introduce SJD-PAC, an enhanced SJD framework. First, SJD-PAC employs a proactive drafting strategy to improve local acceptance rates in these challenging high-entropy regions. Second, we introduce an adaptive continuation mechanism that sustains sequence validation after an initial rejection, bypassing the need for full resampling. Working in tandem, these optimizations significantly increase the average acceptance length per step, boosting inference speed while strictly preserving the target distribution. Experiments on standard text-to-image benchmarks demonstrate that SJD-PAC achieves a $3.8\times$ speedup with lossless image quality. Code is available at https://github.com/KangJialiang/SJD-PAC.
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。
