-
Notifications
You must be signed in to change notification settings - Fork 30.7k
[CB
] Refactors the way we access paged
#41370
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
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
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! Not sure we can run slow tests for this, but it's worth making sure the example still works with paged|eager
, paged|sdpa
or with paged|flash_attention_2
-- kernels is not available on AMD so we need the classic FA package.
"eager_paged": eager_paged_attention_forward, | ||
"paged|flash_attention2": paged_attention_forward, | ||
"paged|sdpa": sdpa_attention_paged_forward, | ||
"paged|eager": eager_paged_attention_forward, |
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.
should paged|flex_attention
be an option as well? I see it listed below in the tests
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.
Not supported yet AFAIK
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.
Ok good to know 👍 ty
What does this PR do?
The user decides on the function, but CB handles itself which "interface" wrapper to use. This should make stuff easier