New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

怎么benchmark FlashDecoding性能 #27

Open

feifeibear opened this issue Dec 15, 2023 · 1 comment

feifeibear commented Dec 15, 2023

hello开发者，

我看到OpenPPL更新的新闻：
https://mp.weixin.qq.com/s/L35pj8fYakvYnL4LYu6nuw

想测试一下这个项目里flashddecoding的速度。请问怎么能够复现文章中的结果，有没有测试脚本？
另外这个项目里的flashdecoding和flashattn项目里的有什么区别么？

Collaborator

Alcanderian commented Dec 15, 2023 •

edited

Loading

你好，文章中flash decoding的测试结果为llama2 7b整网解码的加速比，可以使用
https://github.com/openppl-public/ppl.nn.llm/blob/master/tools/benchmark_llama.cc
输入相应的参数进行复现，基本使用方法可以参考
https://github.com/openppl-public/ppl.nn.llm/blob/master/tools/benchmark.sh

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment