https://github.com/yichengdwu/flashattention.jl

Julia implementation of the Flash Attention algorithm
https://github.com/yichengdwu/flashattention.jl

cuda-programming deeplearning transfomers

Last synced: 13 days ago
JSON representation

Julia implementation of the Flash Attention algorithm

• Host: GitHub
• URL: https://github.com/yichengdwu/flashattention.jl
• Owner: YichengDWu
• License: mit
• Created: 2023-03-26T02:44:07.000Z (almost 2 years ago)
• Default Branch: master
• Last Pushed: 2023-09-04T13:46:33.000Z (over 1 year ago)
• Last Synced: 2024-11-10T08:40:22.079Z (about 2 months ago)
• Topics: cuda-programming, deeplearning, transfomers
• Language: Julia
• Homepage: https://yichengdwu.github.io/FlashAttention.jl/
• Size: 898 KB
• Stars: 18
• Watchers: 3
• Forks: 1
• Open Issues: 1

Awesome Lists containing this project