Personal blog by Yixiao (Jack) Zenghttps://jackzeng0208.github.io/https://jackzeng0208.github.io/en/blog/speculative-decoding-explained/https://jackzeng0208.github.io/en/blog/speculative-decoding-explained/A deep dive into speculative decoding and how it accelerates large language model inference without sacrificing quality.Sun, 15 Feb 2026 00:00:00 GMT