Skip to content

feat: Add support for is_causal argument in attention #2780

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
Merged
merged 3 commits into from
Apr 30, 2024
Merged

feat: Add support for is_causal argument in attention #2780

merged 3 commits into from
Apr 30, 2024

Conversation

gs-olive
Copy link
Contributor

Description

  • Add support for is_causal argument in attention converter

Type of change

  • New feature (non-breaking change which adds functionality)

Checklist:

  • [ x ] My code follows the style guidelines of this project (You can use the linters)
  • [ x ] I have performed a self-review of my own code
  • [ x ] I have commented my code, particularly in hard-to-understand areas and hacks
  • [ x ] I have made corresponding changes to the documentation
  • [ x ] I have added tests to verify my fix or my feature
  • [ x ] New and existing unit tests pass locally with my changes
  • [ x ] I have added the relevant labels to my PR in so that relevant reviewers are notified

@gs-olive gs-olive requested a review from peri044 April 26, 2024 00:29
@gs-olive gs-olive self-assigned this Apr 26, 2024
@github-actions github-actions bot added component: tests Issues re: Tests component: lowering Issues re: The lowering / preprocessing passes component: conversion Issues re: Conversion stage component: converters Issues re: Specific op converters component: api [Python] Issues re: Python API component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths labels Apr 26, 2024
@gs-olive gs-olive force-pushed the is_causal_support branch from 62878a3 to a81b7f7 Compare April 26, 2024 18:56
peri044
peri044 reviewed Apr 30, 2024
View reviewed changes
py/torch_tensorrt/dynamo/conversion/impl/attention.py
@@ -46,6 +51,17 @@ def scaled_dot_product_attention(
mm,
scale,
)

if is_causal:
Copy link
Collaborator

Choose a reason for hiding this comment

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

This doesn't support dynamic shapes right ?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

The current implementation does not, no

@peri044
Copy link
Collaborator

peri044 commented Apr 30, 2024 •
edited
Loading

Changes LGTM

@gs-olive gs-olive merged commit e6f9aa2 into pytorch:main Apr 30, 2024
@gs-olive gs-olive deleted the is_causal_support branch April 30, 2024 22:34
laikhtewari pushed a commit that referenced this pull request May 24, 2024
@gs-olive @laikhtewari
feat: Add support for is_causal argument in attention (#2780)
588ec96
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@peri044 peri044 peri044 left review comments

Assignees

@gs-olive gs-olive

Labels
cla signed component: api [Python] Issues re: Python API component: conversion Issues re: Conversion stage component: converters Issues re: Specific op converters component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths component: lowering Issues re: The lowering / preprocessing passes component: tests Issues re: Tests
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@gs-olive @peri044 @facebook-github-bot