[Xnnpack] Accept default padding value for torch.constant_pad_nd #7469
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7469
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit f3904a8 with merge base cb568fa ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D67756862 |
pssrawat
changed the title
pssrawat
added a commit
to pssrawat/executorch
that referenced
this pull request
Jan 2, 2025
Summary:
xnnpack delegation for pad op assumes that the pad value is always present. However, constant_pad_nd defults to padding value of 0.0 if it's not present in the op. When absent, it errors out in `padding_value = cast(float, node.args[2])` with `IndexError: tuple index out of range`.
{F1974161274}
This diff defaults to padding value of 0.0 if the arg is absent from torch.constant_pad_nd op.
Differential Revision: D67756862
pssrawat
force-pushed
the
export-D67756862
branch
from
373dcbd to
a694541
Compare
|
This pull request was exported from Phabricator. Differential Revision: D67756862 |
tarun292
approved these changes
Jan 2, 2025
pssrawat
added a commit
to pssrawat/executorch
that referenced
this pull request
Jan 2, 2025
Summary:
xnnpack delegation for pad op assumes that the pad value is always present. However, constant_pad_nd defults to padding value of 0.0 if it's not present in the op. When absent, it errors out in `padding_value = cast(float, node.args[2])` with `IndexError: tuple index out of range`.
{F1974161274}
This diff defaults to padding value of 0.0 if the arg is absent from torch.constant_pad_nd op.
Reviewed By: tarun292
Differential Revision: D67756862
pssrawat
force-pushed
the
export-D67756862
branch
from
a694541 to
7f644f2
Compare
|
This pull request was exported from Phabricator. Differential Revision: D67756862 |
pssrawat
added a commit
to pssrawat/executorch
that referenced
this pull request
Jan 2, 2025
Summary:
xnnpack delegation for pad op assumes that the pad value is always present. However, constant_pad_nd defults to padding value of 0.0 if it's not present in the op. When absent, it errors out in `padding_value = cast(float, node.args[2])` with `IndexError: tuple index out of range`.
{F1974161274}
This diff defaults to padding value of 0.0 if the arg is absent from torch.constant_pad_nd op.
Reviewed By: tarun292
Differential Revision: D67756862
pssrawat
force-pushed
the
export-D67756862
branch
from
7f644f2 to
ae97781
Compare
|
This pull request was exported from Phabricator. Differential Revision: D67756862 |
pssrawat
force-pushed
the
export-D67756862
branch
from
ae97781 to
725294b
Compare
|
This pull request was exported from Phabricator. Differential Revision: D67756862 |
Summary: Pull Request resolved: pytorch#7469 xnnpack delegation for pad op assumes that the pad value is always present. However, constant_pad_nd defults to padding value of 0.0 if it's not present in the op. When absent, it errors out in `padding_value = cast(float, node.args[2])` with `IndexError: tuple index out of range`. {F1974161274} This diff defaults to padding value of 0.0 if the arg is absent from torch.constant_pad_nd op. Reviewed By: tarun292 Differential Revision: D67756862
|
This pull request was exported from Phabricator. Differential Revision: D67756862 |
pssrawat
force-pushed
the
export-D67756862
branch
from
725294b to
f3904a8
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
xnnpack delegation for pad op assumes that the pad value is always present. However, constant_pad_nd defults to padding value of 0.0 if it's not present in the op. When absent, we get the following error in xnnpack delegation:
{F1974161274}
This diff defaults to padding value of 0.0 if the arg is absent from torch.constant_pad_nd op.
Differential Revision: D67756862