Preprint
Aug 2026
LibraSpec: Dynamic Diffusion-Based Speculative Decoding via Marginal-Gain-Driven Optimization
LibraSpec, a training-free and plug-and-play algorithm that iteratively determines the speculative length using drafter confidence scores, is developed and it is proved that LibraSpec monotonically converges toward the optimal speculative length.
Zexun Lin, Yuan Feng, Junlin Lv et al.
· 0 citations