Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Contextual Correction of Parallel Drafts for Speculative Decoding
Roy Eisenstadt, Harel Lidar, Tal Gonen +5
Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target m…
cs.CL2026
To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals
Roy Eisenstadt, Ido Cohen, Edo Cohen-Karlik +2
Speculative Decoding (SD) has significantly accelerated Large Language Model (LLM) inference, yet existing approaches face a fundamental tradeoff between two drafting strategies: n…