-
Notifications
You must be signed in to change notification settings - Fork 746
Arm backend: Replace Tensor_Scalar with Tensor_Tensor in sqrt op #11783
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
base: main
Are you sure you want to change the base?
Conversation
Signed-off-by: Elena Zhelezina <[email protected]> Change-Id: Ia3e596f855ec97b0ad59161bccc906b13e96c770
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11783
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 1 Cancelled Job, 2 Unrelated FailuresAs of commit 1774308 with merge base 121714a ( NEW FAILURES - The following jobs have failed:
CANCELLED JOB - The following job was cancelled. Please retry:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
fails in 2 Arm jobs, trying a rebase to see if it helps |
|
Please rebase? |
digantdesai
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM at a high level, left some comments.
|
|
||
| input_quantized = input_quantized or all( | ||
| (input_node.target in dq_ops) | ||
| or (node.name == "aten_pow_tensor_tensor") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why are we using name here? Also didn't we already have support for torch.ops.aten.pow.Tensor_Tensor?
| exir_ops.edge.aten.squeeze_copy.dims, | ||
| exir_ops.edge.aten.pow.Tensor_Scalar, | ||
| exir_ops.edge.aten.pow.Tensor_Tensor, | ||
| torch.ops.aten.pow.Tensor_Tensor, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why add aten target too?
| torch.ops.aten.hardswish_.default, | ||
| torch.ops.aten.full_like.default, | ||
| torch.ops.aten.pow.Tensor_Scalar, | ||
| torch.ops.aten.pow.Tensor_Tensor, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add BI + quantize tests in test_pow.py?
| """ | ||
| if node.op == "placeholder": | ||
| # node is an input, weight or bias node | ||
| if not node.users: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nit: move the comment?
|
This will unfortunately need a rebase after the TOSA 0.80.1 removal :( |
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
Arm backend: Replace Tensor_Scalar with Tensor_Tensor in sqrt op
Change-Id: Ia3e596f855ec97b0ad59161bccc906b13e96c770
Signed-off-by: Elena Zhelezina [email protected]
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218