A survey of techniques for optimizing transformer inference-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

A survey of techniques for optimizing transformer inference

Published:2023-11 Issue: Volume:144 Page:102990
ISSN:1383-7621
Container-title:Journal of Systems Architecture
language:en
Short-container-title:Journal of Systems Architecture

Author:

Chitty-Venkata Krishna Teja,Mittal Sparsh^ORCID,Emani Murali,Vishwanath Venkatram,Somani Arun K.

Funder

US Department of Energy

Semiconductor Research Corporation

Science and Engineering Research Board

Intel Corporation

Office of Science

Oak Ridge National Laboratory

National Science Foundation

Iowa State University

Illinois State University

Publisher

Elsevier BV

Subject

Hardware and Architecture,Software

Reference270 articles.

1. Artificial intelligence (AI) market size, growth, Report 2022–2030;Research,2022

2. Attention is all you need;Vaswani,2017

3. ChatGPT: Optimizing Language Models for Dialogue;Schulman,2022

4. G. BARD, 2023. URL https://bard.google.com/.

5. GenSLMs: Genome-Scale Language Models Reveal SARS-CoV-2 Evolutionary Dynamics;Zvyagin,2022

Cited by 21 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. FPGA-assisted Design Space Exploration of Parameterized AI Accelerators: A Quickloop Approach;Journal of Systems Architecture;2024-10

2. A survey of FPGA and ASIC designs for transformer inference acceleration and optimization;Journal of Systems Architecture;2024-10

3. A novel iteration scheme with conjugate gradient for faster pruning on transformer models;Complex & Intelligent Systems;2024-08-07

4. Software Optimization and Design Methodology for Low Power Computer Vision Systems;ACM Transactions on Embedded Computing Systems;2024-08-07

5. Swin-FER: Swin Transformer for Facial Expression Recognition;Applied Sciences;2024-07-14

同舟云学术

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