Image de couverture de livre

AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Luo, Shuqing, Guan, Yilin, Li, Pingzhi, Wang, Hanrui, Chen, Tianlong
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Hexa-MoE: Efficient and Heterogeneous-aware Training for Mixture-of-Experts
par: Luo, Shuqing, et autres
Publié: (2024)

AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention
par: Hu, Yuxuan, et autres
Publié: (2026)

AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR
par: Nguyen, Tuan, et autres
Publié: (2025)

Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference
par: Luo, Shuqing, et autres
Publié: (2025)

ATTS: Asynchronous Test-Time Scaling via Conformal Prediction
par: Xiong, Jing, et autres
Publié: (2025)

ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion
par: Khan, Rana Muhammad Shahroz, et autres
Publié: (2025)

Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
par: Sun, Shengyin, et autres
Publié: (2025)

SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
par: Wang, Hanrui, et autres
Publié: (2020)

AsyncSparse: Accelerating Sparse Matrix-Matrix Multiplication on Asynchronous GPU Architectures
par: Liu, Jie, et autres
Publié: (2026)

Can GRPO Help LLMs Transcend Their Pretraining Origin?
par: Ni, Kangqi, et autres
Publié: (2025)

QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts
par: Li, Pingzhi, et autres
Publié: (2024)

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
par: Wang, Yiming, et autres
Publié: (2025)

Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design
par: Zhang, Mohan, et autres
Publié: (2025)

Parallel Loop Transformer for Efficient Test-Time Computation Scaling
par: Wu, Bohong, et autres
Publié: (2025)

Q-Newton: Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent
par: Li, Pingzhi, et autres
Publié: (2024)

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
par: Li, Pingzhi, et autres
Publié: (2023)

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
par: Cui, Chengming, et autres
Publié: (2026)

DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation
par: Li, Pingzhi, et autres
Publié: (2025)

AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
par: Chen, Zigeng, et autres
Publié: (2024)

Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
par: Jin, Tian, et autres
Publié: (2025)

Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling
par: Kuang, Peng, et autres
Publié: (2025)

Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention
par: Xiao, Emily, et autres
Publié: (2025)

TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration
par: Wei, Linye, et autres
Publié: (2026)

An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models
par: Luo, Hanrui, et autres
Publié: (2026)

Glider: Global and Local Instruction-Driven Expert Router
par: Li, Pingzhi, et autres
Publié: (2024)

MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning
par: Chen, Hongwei, et autres
Publié: (2025)

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

Arch: An AI-Native Hardware Description Language for Register-Transfer Clocked Hardware Design
par: Zhao, Shuqing
Publié: (2026)

Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?
par: Li, Pengxiang, et autres
Publié: (2026)

$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
par: Chen, Guanjie, et autres
Publié: (2024)

Divide and Conquer: Accelerating Diffusion-Based Large Language Models via Adaptive Parallel Decoding
par: Luo, Xiangzhong, et autres
Publié: (2026)

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

Accelerate Speculative Decoding with Sparse Computation in Verification
par: Wang, Jikai, et autres
Publié: (2025)

Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner
par: Li, Bolian, et autres
Publié: (2025)

Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence
par: Ghasemabadi, Amirhosein, et autres
Publié: (2025)

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
par: MiniMax, et autres
Publié: (2025)

Efficient Sparse Attention needs Adaptive Token Release
par: Zhang, Chaoran, et autres
Publié: (2024)

AsyncMDE: Real-Time Monocular Depth Estimation via Asynchronous Spatial Memory
par: Ma, Lianjie, et autres
Publié: (2026)

Cascade Reward Sampling for Efficient Decoding-Time Alignment
par: Li, Bolian, et autres
Publié: (2024)

Timely Machine: Awareness of Time Makes Test-Time Scaling Agentic
par: Ma, Yichuan, et autres
Publié: (2026)