Skip to content

Arm backend: Add TOSA support for gt.Scalar and lt.Scalar #9908

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

Merged
merged 5 commits into from
Apr 11, 2025

Conversation

YufengShi-dudu
Copy link
Collaborator

@YufengShi-dudu YufengShi-dudu commented Apr 4, 2025

  • Convert gt.Scalar and lt.Scalar to gt.Tensor and lt.Tensor
  • Expand the scalar operands to match the shape of the tensor operands
  • Rename the eq test names to include full aten op name

Change-Id: I0756685ce3b1a20a62dc773606cf913f42d59b75

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218

@YufengShi-dudu YufengShi-dudu added partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm ciflow/trunk topic: not user facing labels Apr 4, 2025
Copy link

pytorch-bot bot commented Apr 4, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9908

Note: Links to docs will display an error until the docs builds have been completed.

⏳ No Failures, 2 Pending

As of commit dadffd0 with merge base 91a14f1 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Apr 4, 2025
@YufengShi-dudu
Copy link
Collaborator Author

Need to change the number of torch.ops.higher_order.executorch_call_delegate in test_where.py due to this pull request: #9869

- Convert gt.Scalar and lt.Scalar to gt.Tensor and lt.Tensor
- Expand the scalar operands to match the shape of the tensor operands
- Rename the eq test names to include full aten op name
- Update the test_where.py due to the support of gt.Scalar

Change-Id: I0756685ce3b1a20a62dc773606cf913f42d59b75
Signed-off-by: Yufeng Shi <yufeng.shi@arm.com>
@zingo zingo merged commit 80400f6 into pytorch:main Apr 11, 2025
167 checks passed
kirklandsign pushed a commit that referenced this pull request Apr 11, 2025
- Convert gt.Scalar and lt.Scalar to gt.Tensor and lt.Tensor
- Expand the scalar operands to match the shape of the tensor operands
- Rename the eq test names to include full aten op name

Signed-off-by: Yufeng Shi <yufeng.shi@arm.com>
keyprocedure pushed a commit to keyprocedure/executorch that referenced this pull request Apr 21, 2025
- Convert gt.Scalar and lt.Scalar to gt.Tensor and lt.Tensor
- Expand the scalar operands to match the shape of the tensor operands
- Rename the eq test names to include full aten op name

Signed-off-by: Yufeng Shi <yufeng.shi@arm.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ciflow/trunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm topic: not user facing
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants