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

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding

Yuhao Shen, Tianyu Liu, Xinyi Hu +9

Speculative decoding (SD) accelerates large language model inference by leveraging a draft-then-verify paradigm. To maximize the acceptance rate, recent methods construct expansive…