Skip to content
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.

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

[Inference] Fused Moe Optimization #70059

Merged
merged 13 commits into from
Dec 28, 2024
Merged

Conversation

CJ77Qi
Copy link
Contributor

@CJ77Qi CJ77Qi commented Dec 9, 2024

PR Category

Inference

PR Types

New features

Description

Pcard-71500

优化fused_moe配置选择,运行时针对不同m维度大小tune

Copy link

paddle-bot bot commented Dec 9, 2024

你的PR提交成功,感谢你对开源项目的贡献!
请关注后续CI自动化测试结果,详情请参考Paddle-CI手册
Your PR has been submitted. Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

@CJ77Qi CJ77Qi changed the title [Inference] Moe [Inference] Fused Moe Optimization Dec 9, 2024
std::vector<int> occupancies(candidate_configs.size());
auto& moeGemmConfigManager = phi::MoEGemmConfigManager::Instance();
static constexpr int warm_time = 5;
static constexpr int test_time = 10;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这两个参数最好是能支持修改。

@zhoutianzi666 zhoutianzi666 merged commit fc4ff25 into PaddlePaddle:develop Dec 28, 2024
29 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants