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.

Sign up for GitHub

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

Jump to bottom

[MLIR][TORCH] Add support for enable_gqa flag in SDPA op #3950

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[MLIR][TORCH] Add support for enable_gqa flag in SDPA op #3950

wants to merge 2 commits into from
+153 −5

Conversation

vivekkhandelwal1
Copy link
Collaborator

No description provided.

pashu123
pashu123 approved these changes Jan 9, 2025
View reviewed changes
Copy link
Member

@pashu123 pashu123 left a comment

Choose a reason for hiding this comment

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

LGTM! Are there any reasons why we aren't decomposing this torch op into another set of torch ops?

@vivekkhandelwal1
Copy link
Collaborator Author

LGTM! Are there any reasons why we aren't decomposing this torch op into another set of torch ops?

AFAIK, the reason for not doing that is since we want the attention op as a single kernel. Hence, we just lower it to tm_tensor.attention and the rest is taken care of during the codegen.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@pashu123 pashu123 pashu123 approved these changes

@rsuderman rsuderman Awaiting requested review from rsuderman

@AmosLewis AmosLewis Awaiting requested review from AmosLewis

@zjgarvey zjgarvey Awaiting requested review from zjgarvey

@Groverkss Groverkss Awaiting requested review from Groverkss

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@vivekkhandelwal1 @pashu123