Tag
PRESTO introduces a prefix-aligned tree drafting framework for diffusion speculative decoding, achieving up to 1.5x speedup on dedicated diffusion drafters and 1.12x on self-speculative diffusion LLMs.
Proposes Progressive Tree Drafting (PTD), a training-free, model-agnostic speculative decoding method that uses progressive tree structures and stepwise pruning to enable parallel generation of multiple draft paths, achieving up to 2x speedup on various benchmarks.
DominoTree introduces a training-free best-first draft tree for speculative decoding that uses conditional (non-factorized) correction from Domino to achieve up to 6.6x speedup over autoregressive decoding and the highest mean accept length across evaluated methods on Qwen3 models.
JetSpec is a speculative decoding framework that combines efficient forward drafting with causal conditioning to improve LLM inference speed and acceptance rates, achieving up to 9.64x speedup on MATH-500 and 4.58x on conversational workloads.
This paper introduces SpecBlock, a block-iterative speculative decoding method that combines path dependence with efficient drafting to accelerate LLM inference. It demonstrates improved speedup over existing methods like EAGLE-3 while maintaining lower drafting costs.