-
Notifications
You must be signed in to change notification settings - Fork 405
Misc CoopMat/lambda expr fixes. #9685
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
Conversation
|
/format |
|
🌈 Formatted, please merge the changes from this PR |
kaizhangNV
left a comment
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.
Just one suggestion, hopefully we can make the flash attention tests as a verifiable executable test, instead of just a compile test.
| should only perform uniform operations for portability. If your code specifies a combination | ||
| that is not supported by the device, the behavior is undefined. | ||
|
|
||
| Additionally, while only `MemoryScope.Subgroup` (warp-level cooperation) is supported on 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.
Looks like we can also support this on cuda as well.
849a5d1
No description provided.