Image de couverture de livre

Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Shengyin, Li, Yiming, Li, Xing, Lian, Yingzhao, Lin, Weizhe, Zhen, Hui-Ling, Yang, Zhiyuan, Chen, Chen, Yu, Xianzhi, Yuan, Mingxuan, Ma, Chen
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
par: Sun, Shengyin, et autres
Publié: (2026)

Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence
par: Sun, Shengyin, et autres
Publié: (2026)

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
par: Lin, Weizhe, et autres
Publié: (2025)

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
par: Zhang, Jiebin, et autres
Publié: (2026)

Iterative Deepening Sampling as Efficient Test-Time Scaling
par: Chen, Weizhe, et autres
Publié: (2025)

MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling
par: Zhang, Yu, et autres
Publié: (2025)

DiLA: Enhancing LLM Tool Learning with Differential Logic Layer
par: Zhang, Yu, et autres
Publié: (2024)

SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention
par: Yankun, Hong, et autres
Publié: (2025)

SwiftMem: Fast Agentic Memory via Query-aware Indexing
par: Tian, Anxin, et autres
Publié: (2026)

PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers
par: Lin, Weizhe, et autres
Publié: (2024)

Towards Efficient Agents: A Co-Design of Inference Architecture and System
par: Lin, Weizhe, et autres
Publié: (2025)

Scaling Laws for Speculative Decoding
par: Yan, Siyuan, et autres
Publié: (2025)

LESA: Learnable LLM Layer Scaling-Up
par: Yang, Yifei, et autres
Publié: (2025)

What Matters For Safety Alignment?
par: Li, Xing, et autres
Publié: (2026)

AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding
par: Luo, Shuqing, et autres
Publié: (2025)

Scaling Up Dynamic Human-Scene Interaction Modeling
par: Jiang, Nan, et autres
Publié: (2024)

Enhanced Pre-training of Graph Neural Networks for Million-Scale Heterogeneous Graphs
par: Sun, Shengyin, et autres
Publié: (2025)

Behavioral Fingerprinting of Large Language Models
par: Pei, Zehua, et autres
Publié: (2025)

From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
par: Qu, Xiangyan, et autres
Publié: (2026)

KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
par: Li, Xing, et autres
Publié: (2025)

RTLRewriter: Methodologies for Large Models aided RTL Code Optimization
par: Yao, Xufeng, et autres
Publié: (2024)

FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM Inference
par: Liu, Xing, et autres
Publié: (2025)

Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
par: Tang, Bangsheng, et autres
Publié: (2025)

AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies
par: Zhang, Bo-Wen, et autres
Publié: (2024)

RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
par: Huang, Zhongzhan, et autres
Publié: (2025)

SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation
par: Zhou, Xinyi, et autres
Publié: (2024)

Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios
par: Shi, Luohe, et autres
Publié: (2025)

Benchmark Test-Time Scaling of General LLM Agents
par: Li, Xiaochuan, et autres
Publié: (2026)

Tutorial Proposal: Speculative Decoding for Efficient LLM Inference
par: Xia, Heming, et autres
Publié: (2025)

Scaling Up Active Testing to Large Language Models
par: Berrada, Gabrielle, et autres
Publié: (2025)

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats
par: Zhao, Pengxiang, et autres
Publié: (2026)

An Empirical Study of Speculative Decoding on Software Engineering Tasks
par: Li, Yijia, et autres
Publié: (2026)

Semi-Clairvoyant Scheduling of Speculative Decoding Requests to Minimize LLM Inference Latency
par: Li, Ruixiao, et autres
Publié: (2025)

Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
par: Li, Minghan, et autres
Publié: (2024)

Scaling Up LLM Reviews for Google Ads Content Moderation
par: Qiao, Wei, et autres
Publié: (2024)

Scaling Speculative Decoding with Lookahead Reasoning
par: Fu, Yichao, et autres
Publié: (2025)

RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
par: Zeng, Zhiyuan, et autres
Publié: (2025)

SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search
par: Li, Dong, et autres
Publié: (2025)

Up to Speed on DVD.
par: Crawford, Walt
Publié: (1999)

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding
par: Zhang, Ziyi, et autres
Publié: (2025)