Abstract:Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying them in parallel with a single target model forward pass. However, speculative decoding itself relies on a sequential dependence between speculation and verification. We introduce speculative speculative decoding (SSD) to parallelize these operations. While a verification is ongoing, the draft model predicts likely verification outcomes and prepares speculations pre-emptively for them. If the actual verification outcome is then in the predicted set, a speculation can be returned immediately, eliminating drafting overhead entirely. We identify three key challenges presented by speculative speculative decoding, and suggest principled methods to solve each. The result is Saguaro, an optimized SSD algorithm. Our implementation is up to 2x faster than optimized speculative decoding baselines and up to 5x faster than autoregressive decoding with open source inference engines.
«Били в одно место». Российский газовоз уничтожен украинскими дронами в Средиземном море. Что известно об атаке и судьбе моряков14:20，更多细节参见WPS下载最新地址
На Украине рассказали о технике влияния Ермака на Зеленского14:52。关于这个话题，im钱包官方下载提供了深入分析
Угрозу применения ядерного оружия в конфликте вокруг Ирана оценили14:57