SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
Diffusion large language models (DLLMs) generate text through iterative block denoising, and multi-branch speculative decoding accelerates this process by verifying a main branch together with multiple draft branches in a single forward pass. While prior DLLM acceleration methods primarily exploit temporal redundancy a...
Chung-En Ho, Wei-Yu Sun, Cheng-Jhih Shih et al.
· 0 citations