FlexDraft is a lossless speculative decoding framework that adapts to batch sizes via attention tuning on final layers, MLP-based bonus calibration, and dynamic parallel/sequential decoding.
Pearl: Parallel speculative decoding with adaptive draft length
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
PARD-2 uses Confidence-Adaptive Token optimization to align draft model training with acceptance length in speculative decoding, enabling dual-mode operation and up to 6.94x lossless speedup on Llama3.1-8B.
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.
citing papers explorer
-
FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
FlexDraft is a lossless speculative decoding framework that adapts to batch sizes via attention tuning on final layers, MLP-based bonus calibration, and dynamic parallel/sequential decoding.
-
PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
PARD-2 uses Confidence-Adaptive Token optimization to align draft model training with acceptance length in speculative decoding, enabling dual-mode operation and up to 6.94x lossless speedup on Llama3.1-8B.
-
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.