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

[XPU] add fused_softmax_mask and fused_softmax_mask_grad. #55914

Merged
merged 2 commits into from
Aug 9, 2023

Conversation

houj04
Copy link
Contributor

@houj04 houj04 commented Aug 2, 2023

PR types

New features

PR changes

OPs

Description

增加XPU下面的fused_softmax_mask算子及其反向。

@paddle-bot
Copy link

paddle-bot bot commented Aug 2, 2023

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.

@paddle-bot paddle-bot bot added contributor External developers status: proposed labels Aug 2, 2023
key_seq_len));

PADDLE_ENFORCE_EQ(mask_dim[1],
1,
Copy link
Contributor

Choose a reason for hiding this comment

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

xpu能支持triangle_softmax吗?可以省掉mask的显存占用

Copy link
Contributor Author

Choose a reason for hiding this comment

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

triangle应该也能支持,需要写一个。不过就目前的情况来看,喂进来的mask,并不是一个完全的三角矩阵:
图片

Copy link
Contributor Author

Choose a reason for hiding this comment

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

从代码逻辑上看,走不到triangle的分支上。估计需要改组网或者其它地方。
图片

@houj04 houj04 merged commit b982af4 into PaddlePaddle:develop Aug 9, 2023
@paddle-bot
Copy link

paddle-bot bot commented Aug 9, 2023

你的PR已合入Paddle库,请关注后续测试结果。
Your PR has been merged into the repository. An official integration test will be conducted later. Stay tuned.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
contributor External developers
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants