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

Add dynamic shape support for cumsum/grid #3051

Merged
merged 9 commits into from
Aug 2, 2024
Merged

Add dynamic shape support for cumsum/grid #3051

merged 9 commits into from
Aug 2, 2024

Conversation

lanluo-nvidia
Copy link
Collaborator

Description

Add dynamic shape support for cumsum/grid

Fixes # (issue)

Type of change

Please delete options that are not relevant and/or add your own.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Checklist:

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

@github-actions github-actions bot added component: tests Issues re: Tests 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 Jul 31, 2024
@github-actions github-actions bot requested a review from apbose July 31, 2024 22:27
peri044
peri044 approved these changes Jul 31, 2024
View reviewed changes
Copy link
Collaborator

@peri044 peri044 left a comment

Choose a reason for hiding this comment

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

LGTM, pending CI.

zewenli98
zewenli98 reviewed Aug 1, 2024
View reviewed changes
Copy link
Collaborator

@zewenli98 zewenli98 left a comment

Choose a reason for hiding this comment

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

LGTM, just a few minor comments.

py/torch_tensorrt/dynamo/conversion/impl/slice/ops.py
Comment on lines +397 to +402
# the trip_limit has to be a 0D shape tensor, however this impl.shape.shape gives a 1D shape
# for example if the trip limit is 3, it wants a tensor(3), not a tensor([3])
# in order to reduce it from 1D to 0D, i have to use this impl.reduce.sum
trip_limit = impl.reduce.sum(
ctx, target, source_ir, name, trip_limit, 0, keepdim=False
)
Copy link
Collaborator

Choose a reason for hiding this comment

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

Another way to create a 0D shape tensor you can refer to: https://github.com/pytorch/TensorRT/blob/main/py/torch_tensorrt/dynamo/conversion/impl/embedding.py#L191

py/torch_tensorrt/dynamo/conversion/impl/slice/ops.py Outdated Show resolved Hide resolved
@lanluo-nvidia lanluo-nvidia merged commit a5f4d5b into main Aug 2, 2024
38 of 47 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@zewenli98 zewenli98 zewenli98 left review comments

@peri044 peri044 peri044 approved these changes

@apbose apbose Awaiting requested review from apbose

Assignees
No one assigned
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: tests Issues re: Tests
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@lanluo-nvidia @peri044 @zewenli98 @facebook-github-bot