KMS

浏览/检索结果: 共4条,第1-4条 帮助

  只显示已认领条目
已选(0)清除 条数/页:   排序方式:
Make LLM Inference Affordable to Everyone: Augmenting GPU Memory with NDP-DIMM 会议论文
2025 IEEE INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE COMPUTER ARCHITECTURE (HPCA), Las Vegas, NV, USA, 1-5 March 2025
作者:  Lian Liu;  Shixin Zhao;  Bing Li;  Haimeng Ren;  Zhaohui Xu
Adobe PDF(1300Kb)  |  收藏  |  浏览/下载:30/1  |  提交时间:2025/04/14
COMET: Towards Practical W4A4KV4 LLMs Serving 会议论文
INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS - ASPLOS, Rotterdam, Netherlands, March 30, 2025 - April 3, 2025
作者:  Liu, Lian;  Cheng, Long;  Ren, Haimeng;  Xu, Zhaohui;  Pan, Yudong
Adobe PDF(2187Kb)  |  收藏  |  浏览/下载:28/1  |  提交时间:2025/05/09
COMET: Towards Partical W4A4KV4 LLMs Serving 预印本
2024
作者:  Liu, Lian;  Ren, Haimeng;  Cheng, Long;  Xu, Zhaohui;  Pan, Yudong
Adobe PDF(1293Kb)  |  收藏  |  浏览/下载:176/5  |  提交时间:2024/11/19
ChipGPT: How far are we from natural language hardware design 预印本
2023
作者:  Chang, Kaiyan;  Wang, Ying;  Ren, Haimeng;  Wang, Mengdi;  Liang, Shengwen
Adobe PDF(1684Kb)  |  收藏  |  浏览/下载:209/0  |  提交时间:2024/01/09
  • 首页
  • 上一页
  • 1
  • 下一页
  • 末页