Uh oh!
There was an error while loading. Please reload this page.
[PyTorch] Add sliding window support to FlashAttention - #551
Merged
Conversation
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
cyanguwa
commented
Dec 6, 2023
CollaboratorAuthor
/te-ci |
cyanguwa
commented
Dec 6, 2023
CollaboratorAuthor
/te-ci |
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
cyanguwa
commented
Dec 6, 2023
CollaboratorAuthor
/te-ci pytorch |
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
cyanguwaforce-pushed
the
fa/sliding_window
branch
from
December 7, 2023 23:41
49e147e to
32db392CompareSigned-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
cyanguwa
commented
Dec 8, 2023
CollaboratorAuthor
/te-ci pytorch |
1 similar comment
cyanguwa
commented
Dec 8, 2023
CollaboratorAuthor
/te-ci pytorch |
cyanguwa
commented
Dec 8, 2023
CollaboratorAuthor
Pipeline 11331817 |
CollaboratorAuthor
With newer cuDNN, pipeline 11412889 is green! |
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>
cyanguwa
commented
Dec 13, 2023
CollaboratorAuthor
/te-ci pytorch |
ptrendx
reviewed
Dec 15, 2023
Uh oh!
There was an error while loading. Please reload this page.
ptrendx
reviewed
Dec 15, 2023
Uh oh!
There was an error while loading. Please reload this page.
ptrendx
reviewed
Dec 15, 2023
Uh oh!
There was an error while loading. Please reload this page.
ptrendx
reviewed
Dec 15, 2023
Uh oh!
There was an error while loading. Please reload this page.
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
cyanguwa
commented
Dec 15, 2023
CollaboratorAuthor
/te-ci pytorch |
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
ptrendx
reviewed
Dec 15, 2023
Uh oh!
There was an error while loading. Please reload this page.
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
cyanguwa
commented
Dec 15, 2023
CollaboratorAuthor
/te-ci pytorch |
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
cyanguwa
commented
Dec 15, 2023
CollaboratorAuthor
/te-ci pytorch |
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
cyanguwa
commented
Dec 15, 2023
CollaboratorAuthor
/te-ci pytorch |
ashvinnihalani
commented
Mar 7, 2024
Also want to add a comment that what happens when we want to use grouped query attention with unfused attention. Right now it seems like it errors out. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR only makes changes on the PyTorch side. It
TransformerLayer,MultiHeadAttention,DotProductAttentionandFlashAttentionUnfusedDotProductAttentionarbitrary mask, generated based on the window sizeuse_unfused_attentionflag and exception when none of the three DPA backends are available