Scalable Heterogeneous Scheduling Based Model Parallelism for Real-Time Inference of Large-Scale Deep Neural Networks-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Scalable Heterogeneous Scheduling Based Model Parallelism for Real-Time Inference of Large-Scale Deep Neural Networks

Published:2024-08 Issue:4 Volume:8 Page:2962-2973
ISSN:2471-285X
Container-title:IEEE Transactions on Emerging Topics in Computational Intelligence
language:
Short-container-title:IEEE Trans. Emerg. Top. Comput. Intell.

Author:

Zou Xiaofeng¹^ORCID,Chen Cen¹^ORCID,Lin Peiying²^ORCID,Zhang Luochuan¹^ORCID,Xu Yanwu¹^ORCID,Zhang Wenjie³^ORCID

Affiliation:

1. School of Future Technology, South China University of Technology, Guangzhou, China

2. School of Computer Science & School of Cyberspace Science, Xiangtan University (XTU), Xiangtan, China

3. Department of Electrical Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong

Funder

National Funding Program for Postdoctoral Researchers

Fundamental Research Funds for the Central Universities

Natural Science Foundation of Guangdong Province of China

CCF-Phytium Fund and CAAI-MindSpore Open Fund

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/7433297/10607834/10462579.pdf?arnumber=10462579

Reference47 articles.

1. Fine-grained Cross-modal Alignment Network for Text-Video Retrieval

2. Multilevel Attention Based U-Shape Graph Neural Network for Point Clouds Learning

3. Attention-Aware Encoder–Decoder Neural Networks for Heterogeneous Graphs of Things

4. Language models are few-shot learners;Brown,2020

5. DyGNN: Algorithm and Architecture Support of Dynamic Pruning for Graph Neural Networks

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