Cost-Aware Diffusion Draft Trees for Speculative Decoding 事件

Cost-Aware Diffusion Draft Trees for Speculative Decoding arXiv:2606.01813v1 Announce Type: new Abstract: Speculative decoding accelerates inference by having a lightweight drafter propose tokens verified in parallel by the target language model. Block diffusion drafters such as DFlash generate an entire draft block in one pass, yielding per-position marginals; DDTree uses these to build a candidate tree that maximizes expected acceptance length under a fixed node budget. We observe, however, t