Speculative Verification adds a companion model that estimates draft-target alignment via information gain to dynamically set verification length, delivering up to 2x speedup over standard speculative decoding across tested models and batch sizes.
Kangaroo: Lossless self-speculative decoding for accelerating LLMs via double early exiting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
Speculative Verification adds a companion model that estimates draft-target alignment via information gain to dynamically set verification length, delivering up to 2x speedup over standard speculative decoding across tested models and batch sizes.