ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention
Author:
Affiliation:
1. Rice University,Houston,TX
2. Georgia Institute of Technology,Atlanta,GA
3. Nanjing University,Nanjing
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/10070856/10070923/10071081.pdf?arnumber=10071081
Reference51 articles.
1. Fine-tune BERT with Sparse Self-Attention Mechanism
2. Adaptively Sparse Transformers
3. Bert: Pre-training of deep bidirectional transformers for language understanding;devlin,2018
4. Imagenet: A large-scale hierarchical image database;deng;2009 IEEE Conference on Computer Vision and Pattern Recognition,2009
5. Rethinking attention with performers;choromanski,0
Cited by 17 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. A survey of FPGA and ASIC designs for transformer inference acceleration and optimization;Journal of Systems Architecture;2024-10
2. CoDA: A Co-Design Framework for Versatile and Efficient Attention Accelerators;IEEE Transactions on Computers;2024-08
3. PIM GPT a hybrid process in memory accelerator for autoregressive transformers;npj Unconventional Computing;2024-07-25
4. Joint features-guided linear transformer and CNN for efficient image super-resolution;International Journal of Machine Learning and Cybernetics;2024-07-09
5. ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching;2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA);2024-06-29
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3