-
Notifications
You must be signed in to change notification settings - Fork 5.8k
[DCU] fix topp kernel #66630
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
[DCU] fix topp kernel #66630
Conversation
你的PR提交成功,感谢你对开源项目的贡献! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
@@ -919,8 +919,13 @@ __global__ void topp_sampling_ft(T* sorted_probs, | |||
} | |||
} | |||
if (!skip) { | |||
#ifdef PADDLE_WITH_CUDA |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
我觉得这一部分要调换一下逻辑,用PADDLE_WITH_HIP来判断,和前面语义保持一致会比较好~
LGTM |
* [DCU] fix topp * fix * fix
PR Category
Custom Device
PR Types
Bug fixes
Description
card-85848
fix warp_size and mismatched types in top_p_sampling kernels