most citedSpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism

Yuhao Shen, Tianyu Liu, Junyi Shen +4

Parallel Speculative Decoding (PSD) accelerates traditional Speculative Decoding (SD) by overlapping draft generation with verification. However, it remains hampered by two fundame…