Image de couverture de livre

KVBuffer: IO-aware Serving for Linear Attention

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zou, Longwei, Zhong, Lin
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Kaczmarz Linear Attention
par: Zou, Jiaxuan, et autres
Publié: (2026)

SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
par: Guo, Wentao, et autres
Publié: (2025)

Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving
par: Zhou, Qihui, et autres
Publié: (2025)

Enhancing Linear Attention with Residual Learning
par: Lai, Xunhao, et autres
Publié: (2025)

Toward Carbon-Neutral Human AI: Rethinking Data, Computation, and Learning Paradigms for Sustainable Intelligence
par: Santosh, KC, et autres
Publié: (2025)

Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning
par: Wang, Longwei, et autres
Publié: (2024)

Bridging Interpretability and Robustness Using LIME-Guided Model Refinement
par: Nayyem, Navid, et autres
Publié: (2024)

Exact Linear Attention
par: Ou, Weinuo
Publié: (2026)

Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads
par: Song, Chendong, et autres
Publié: (2026)

ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
par: Niu, Yue, et autres
Publié: (2024)

Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression
par: Zuo, Yifei, et autres
Publié: (2025)

Transolver is a Linear Transformer: Revisiting Physics-Attention through the Lens of Linear Attention
par: Hu, Wenjie, et autres
Publié: (2025)

Lipschitz-aware Linearity Grafting for Certified Robustness
par: Han, Yongjin, et autres
Publié: (2025)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
par: Chou, Yuhong, et autres
Publié: (2024)

Adaptive Memory Decay for Log-Linear Attention
par: Amin, Yaxita, et autres
Publié: (2026)

State Rank Dynamics in Linear Attention LLMs
par: Sun, Ao, et autres
Publié: (2026)

Linear Attention is Enough in Spatial-Temporal Forecasting
par: Ning, Xinyu
Publié: (2024)

Linear Attention for Efficient Bidirectional Sequence Modeling
par: Afzal, Arshia, et autres
Publié: (2025)

On Efficient Scaling of GNNs via IO-Aware Layers Implementations
par: Fomina, Daria, et autres
Publié: (2026)

BoA: Attention-aware Post-training Quantization without Backpropagation
par: Kim, Junhan, et autres
Publié: (2024)

LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid
par: Sun, Weigao, et autres
Publié: (2025)

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
par: Beck, Maximilian, et autres
Publié: (2025)

Beyond Linearity in Attention Projections: The Case for Nonlinear Queries
par: Karbevski, Marko
Publié: (2026)

ZeroS: Zero-Sum Linear Attention for Efficient Transformers
par: Lu, Jiecheng, et autres
Publié: (2026)

Superiority of Multi-Head Attention in In-Context Linear Regression
par: Cui, Yingqian, et autres
Publié: (2024)

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory
par: Huang, Lin, et autres
Publié: (2026)

RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts
par: Joshi, Sahil, et autres
Publié: (2025)

Parrot: Efficient Serving of LLM-based Applications with Semantic Variable
par: Lin, Chaofan, et autres
Publié: (2024)

Efficient High-Accuracy PDEs Solver with the Linear Attention Neural Operator
par: Zhong, Ming, et autres
Publié: (2025)

FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving
par: Ye, Zihao, et autres
Publié: (2025)

Learning under Quantization for High-Dimensional Linear Regression
par: Zhang, Dechen, et autres
Publié: (2025)

Higher-order Linear Attention
par: Zhang, Yifan, et autres
Publié: (2025)

Learning Advanced Self-Attention for Linear Transformers in the Singular Value Domain
par: Wi, Hyowon, et autres
Publié: (2025)

LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention
par: Khosravi, Hamed, et autres
Publié: (2025)

Revisiting Service Level Objectives and System Level Metrics in Large Language Model Serving
par: Wang, Zhibin, et autres
Publié: (2024)

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
par: You, Haoran, et autres
Publié: (2024)

Distance-aware Attention Reshaping: Enhance Generalization of Neural Solver for Large-scale Vehicle Routing Problems
par: Wang, Yang, et autres
Publié: (2024)

TA-RNN: an Attention-based Time-aware Recurrent Neural Network Architecture for Electronic Health Records
par: Olaimat, Mohammad Al, et autres
Publié: (2024)

MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches
par: Wang, Xin, et autres
Publié: (2026)

Scaling Laws for Precision in High-Dimensional Linear Regression
par: Zhang, Dechen, et autres
Publié: (2026)