Cover Image

Accelerate Speculative Decoding with Sparse Computation in Verification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jikai, Tan, Jianchao, Hu, Yuxuan, Qin, Jiayu, Sun, Yerui, Xie, Yuchen, Cai, Xunliang, Li, Juntao, Zhang, Min
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
by: Hu, Yuxuan, et al.
Published: (2025)

AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention
by: Hu, Yuxuan, et al.
Published: (2026)

MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training
by: Li, Jiacheng, et al.
Published: (2026)

C2T: A Classifier-Based Tree Construction Method in Speculative Decoding
by: Huo, Feiye, et al.
Published: (2025)

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification
by: Wang, Jikai, et al.
Published: (2025)

AFA-LoRA: Enabling Non-Linear Adaptations in LoRA with Activation Function Annealing
by: Li, Jiacheng, et al.
Published: (2025)

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures
by: Qin, Jiayu, et al.
Published: (2025)

OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure
by: Wang, Jikai, et al.
Published: (2024)

SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention
by: Xu, Hongtao, et al.
Published: (2026)

WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling
by: Li, Jiacheng, et al.
Published: (2025)

Efficient Reasoning for LLMs through Speculative Chain-of-Thought
by: Wang, Jikai, et al.
Published: (2025)

FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control
by: Sun, Pingwei, et al.
Published: (2026)

Block Verification Accelerates Speculative Decoding
by: Sun, Ziteng, et al.
Published: (2024)

Graph-Structured Speculative Decoding
by: Gong, Zhuocheng, et al.
Published: (2024)

SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
by: Lin, Yijun, et al.
Published: (2026)

Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism
by: Liu, Jiahao, et al.
Published: (2024)

Traversal Verification for Speculative Tree Decoding
by: Weng, Yepeng, et al.
Published: (2025)

SAM Decoding: Speculative Decoding via Suffix Automaton
by: Hu, Yuxuan, et al.
Published: (2024)

Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
by: Kim, Sungkyun, et al.
Published: (2025)

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation
by: Liu, Tianyu, et al.
Published: (2025)

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
by: Xia, Heming, et al.
Published: (2024)

Speculative Decoding for Multi-Sample Inference
by: Li, Yiwei, et al.
Published: (2025)

Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
by: Su, Xin, et al.
Published: (2026)

SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding
by: Sun, Ryan, et al.
Published: (2024)

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding
by: Sun, Shuoyang, et al.
Published: (2026)

Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models
by: Mamou, Jonathan, et al.
Published: (2024)

Self Speculative Decoding for Diffusion Large Language Models
by: Gao, Yifeng, et al.
Published: (2025)

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
by: Zhang, Yifan, et al.
Published: (2026)

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
by: Lin, Gang, et al.
Published: (2026)

Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration
by: Wu, Pengfei, et al.
Published: (2024)

Hierarchical Verification of Speculative Beams for Accelerating LLM Inference
by: Sen, Jaydip, et al.
Published: (2025)

SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding
by: Wang, Zhenglin, et al.
Published: (2024)

NanoSpec: Accelerating Speculative Decoding using Minimalist In-Context Vocabularies
by: Chen, Zhiyang, et al.
Published: (2026)

Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding
by: Pan, Lehan, et al.
Published: (2026)

EAGLE-Pangu: Accelerator-Safe Tree Speculative Decoding on Ascend NPUs
by: Han, Chang, et al.
Published: (2026)

Accelerating Speculative Decoding with Block Diffusion Draft Trees
by: Ringel, Liran, et al.
Published: (2026)

Speculative Decoding with a Speculative Vocabulary
by: Williams, Miles, et al.
Published: (2026)

Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
by: Zhang, Jun, et al.
Published: (2023)

EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference
by: Qian, Yulei, et al.
Published: (2024)

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
by: Yang, Penghui, et al.
Published: (2025)