Preprint
Jul 2026
Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting
Progressive Tree Drafting (PTD) is proposed, which employs a structured, guided parallel drafting strategy to harness the model's parallel potential by coupling a progressive tree structure with a stepwise pruning mechanism and actively guides the LLM to explore multiple semantic paths in a single forward pass.
Zipeng Gao, Zhi Zheng, Qingrong Xia et al.
· 0 citations