Cover Image

SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bang, Jehyeon, Cho, Eunyeong, Hwang, Ranggi, Chung, Jinha, Rhu, Minsoo
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models
by: Cho, Eunyeong, et al.
Published: (2026)

SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG Decoding
by: Darankoum, Davy, et al.
Published: (2026)

Agent-X: Full Pipeline Acceleration of On-device AI Agents
by: Chung, Jinha, et al.
Published: (2026)

Debunking the CUDA Myth Towards GPU-based AI Systems
by: Lee, Yunjae, et al.
Published: (2024)

vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Training
by: Bang, Jehyeon, et al.
Published: (2023)

Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference
by: Hwang, Ranggi, et al.
Published: (2023)

The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective
by: Kim, Jiin, et al.
Published: (2025)

MoE-Spec: Expert Budgeting for Efficient Speculative Decoding
by: McDanel, Bradley, et al.
Published: (2026)

FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM Inference
by: Liu, Xing, et al.
Published: (2025)

SpecMD: A Comprehensive Study On Speculative Expert Prefetching
by: Hoang, Duc, et al.
Published: (2026)

Speculating Experts Accelerates Inference for Mixture-of-Experts
by: Madan, Vivan, et al.
Published: (2026)

SpecVLM: Fast Speculative Decoding in Vision-Language Models
by: Huang, Haiduo, et al.
Published: (2025)

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
by: Pan, Rui, et al.
Published: (2025)

CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
by: Ning, Zhiyuan, et al.
Published: (2025)

LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
by: Lim, Juntaek, et al.
Published: (2024)

Utility-Driven Speculative Decoding for Mixture-of-Experts
by: Saxena, Anish, et al.
Published: (2025)

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
by: Tiwari, Rishabh, et al.
Published: (2025)

SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences
by: Cha, Jungyoub, et al.
Published: (2025)

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
by: Hou, Yunlong, et al.
Published: (2025)

FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference
by: Bajpai, Divya Jyoti, et al.
Published: (2025)

PREBA: A Hardware/Software Co-Design for Multi-Instance GPU based AI Inference Servers
by: Yeo, Gwangoo, et al.
Published: (2024)

PreSto: An In-Storage Data Preprocessing System for Training Recommendation Models
by: Lee, Yunjae, et al.
Published: (2024)

DistillSpec: Improving Speculative Decoding via Knowledge Distillation
by: Zhou, Yongchao, et al.
Published: (2023)

HiSpec: Hierarchical Speculative Decoding for LLMs
by: Kumar, Avinash, et al.
Published: (2025)

KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
by: Cha, Seongjin, et al.
Published: (2026)

SpecMemo: Speculative Decoding is in Your Pocket
by: Yildirim, Selin, et al.
Published: (2025)

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
by: Huang, Kaixuan, et al.
Published: (2024)

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

Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
by: Liu, Baihui, et al.
Published: (2026)

DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
by: Li, Guanghao, et al.
Published: (2025)

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

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
by: Li, Shenggui, et al.
Published: (2026)

EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter Adaptation
by: Zhang, Shuyu, et al.
Published: (2026)

SpecTr: Fast Speculative Decoding via Optimal Transport
by: Sun, Ziteng, et al.
Published: (2023)

Mixture of Attentions For Speculative Decoding
by: Zimmer, Matthieu, et al.
Published: (2024)

SpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism
by: Shen, Yuhao, et al.
Published: (2025)

MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization
by: Zhao, Zhixiong, et al.
Published: (2026)

ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts
by: Georganas, Evangelos, et al.
Published: (2025)

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
by: Wang, Songsheng, et al.
Published: (2025)

Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference
by: Qin, Zongyue, et al.
Published: (2024)