咨询与建议

限定检索结果

文献类型

  • 1 篇 期刊文献
  • 1 篇 会议

馆藏范围

  • 2 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 2 篇 工学
    • 2 篇 计算机科学与技术...
    • 1 篇 电气工程
    • 1 篇 控制科学与工程
  • 1 篇 管理学
    • 1 篇 管理科学与工程(可...

主题

  • 2 篇 model parallelis...
  • 2 篇 deep learning sy...
  • 2 篇 distributed tran...
  • 1 篇 runtime
  • 1 篇 parallel process...
  • 1 篇 throughput
  • 1 篇 transformers
  • 1 篇 planning
  • 1 篇 computational mo...
  • 1 篇 hardware
  • 1 篇 edge computing
  • 1 篇 data models
  • 1 篇 adaptation model...
  • 1 篇 distributed data...

机构

  • 2 篇 sun yat sen univ...

作者

  • 2 篇 wei yuanxin
  • 2 篇 ye shengyuan
  • 2 篇 jiang jiazhi
  • 2 篇 lu yutong
  • 2 篇 chen xu
  • 2 篇 du jiangsu
  • 2 篇 huang dan

语言

  • 2 篇 英文
检索条件"主题词=distributed transformer inference"
2 条 记 录,以下是1-10 订阅
排序:
Communication-Efficient Model Parallelism for distributed In-Situ transformer inference
Communication-Efficient Model Parallelism for Distributed In...
收藏 引用
27th Design, Automation and Test in Europe Conference and Exhibition (DATE)
作者: Wei, Yuanxin Ye, Shengyuan Jiang, Jiazhi Chen, Xu Huang, Dan Du, Jiangsu Lu, Yutong Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China
transformer models have shown significant success in a wide range of tasks. Meanwhile, massive resources required by its inference prevent scenarios with resource-constrained devices from in-situ deployment, leaving a... 详细信息
来源: 评论
Co-Designing transformer Architectures for distributed inference With Low Communication
收藏 引用
IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2025年 第4期36卷 717-730页
作者: Du, Jiangsu Wei, Yuanxin Ye, Shengyuan Jiang, Jiazhi Chen, Xu Huang, Dan Lu, Yutong Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510275 Peoples R China
transformer models have shown significant success in a wide range of tasks. However, the massive resources required for its inference prevent deployment on a single device with relatively constrainted resources, thus ... 详细信息
来源: 评论