SpecBlock achieves 8-13% higher mean speedup than EAGLE-3 at 44-52% drafting cost via block-iterative drafting with hidden-state inheritance, dynamic rank-head branching, valid-prefix masking, and optional cost-aware bandit adaptation.
Kangaroo: Lossless self-speculative decoding via double early exiting
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Coordinating layer-wise and sentence-wise early exits in LLMs produces multiplicative speedups of 1.4-2.3x over single-dimension early exit on sentiment classification tasks.
DREAM-S combines neural architecture search, target-aware supernet training, and attention-entropy-guided distillation to accelerate speculative decoding in VLMs, reporting up to 3.85x speedup over standard methods.
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
citing papers explorer
-
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
SpecBlock achieves 8-13% higher mean speedup than EAGLE-3 at 44-52% drafting cost via block-iterative drafting with hidden-state inheritance, dynamic rank-head branching, valid-prefix masking, and optional cost-aware bandit adaptation.
-
Two-dimensional early exit optimisation of LLM inference
Coordinating layer-wise and sentence-wise early exits in LLMs produces multiplicative speedups of 1.4-2.3x over single-dimension early exit on sentiment classification tasks.
-
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
DREAM-S combines neural architecture search, target-aware supernet training, and attention-entropy-guided distillation to accelerate speculative decoding in VLMs, reporting up to 3.85x speedup over standard methods.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.