Modifying permute op to support all tensor packing. #9215
Merged
+60
−54
Conversation
This file contains hidden or 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/9215
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 572a3dc with merge base 753da9a ( 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: D70587814 |
SS-JIA
approved these changes
Mar 13, 2025
trivedivivek
added a commit
to trivedivivek/executorch
that referenced
this pull request
Mar 13, 2025
Summary: This diff updates Executorch Vulkan backend's `permute` operation to support width, height and channel packed tensors. It also updates the op_registry.py file to register the `permute` operation and adds a new test case to the cases.py file to test the operation. Additionally, it updates the Permute.cpp file to check for the same packed dimension in the input and output tensors, and updates the cases.py file to include the utils::kWidthPacked, utils::kHeightPacked, and utils::kChannelsPacked layouts. Reviewed By: SS-JIA Differential Revision: D70587814
trivedivivek
force-pushed
the
export-D70587814
branch
from
49999af to
692a43b
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70587814 |
trivedivivek
added a commit
to trivedivivek/executorch
that referenced
this pull request
Mar 13, 2025
Summary: Pull Request resolved: pytorch#9215 This diff updates Executorch Vulkan backend's `permute` operation to support width, height and channel packed tensors. It also updates the op_registry.py file to register the `permute` operation and adds a new test case to the cases.py file to test the operation. Additionally, it updates the Permute.cpp file to check for the same packed dimension in the input and output tensors, and updates the cases.py file to include the utils::kWidthPacked, utils::kHeightPacked, and utils::kChannelsPacked layouts. Reviewed By: SS-JIA Differential Revision: D70587814
trivedivivek
force-pushed
the
export-D70587814
branch
from
692a43b to
5e06dd9
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70587814 |
trivedivivek
added a commit
to trivedivivek/executorch
that referenced
this pull request
Mar 13, 2025
Summary: This diff updates Executorch Vulkan backend's `permute` operation to support width, height and channel packed tensors. It also updates the op_registry.py file to register the `permute` operation and adds a new test case to the cases.py file to test the operation. Additionally, it updates the Permute.cpp file to check for the same packed dimension in the input and output tensors, and updates the cases.py file to include the utils::kWidthPacked, utils::kHeightPacked, and utils::kChannelsPacked layouts. Reviewed By: SS-JIA Differential Revision: D70587814
trivedivivek
force-pushed
the
export-D70587814
branch
from
5e06dd9 to
af8b4ad
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70587814 |
trivedivivek
added a commit
to trivedivivek/executorch
that referenced
this pull request
Mar 13, 2025
Summary: This diff updates Executorch Vulkan backend's `permute` operation to support width, height and channel packed tensors. It also updates the op_registry.py file to register the `permute` operation and adds a new test case to the cases.py file to test the operation. Additionally, it updates the Permute.cpp file to check for the same packed dimension in the input and output tensors, and updates the cases.py file to include the utils::kWidthPacked, utils::kHeightPacked, and utils::kChannelsPacked layouts. Reviewed By: SS-JIA Differential Revision: D70587814
trivedivivek
force-pushed
the
export-D70587814
branch
from
af8b4ad to
de14c21
Compare
trivedivivek
added a commit
to trivedivivek/executorch
that referenced
this pull request
Mar 13, 2025
Summary: This diff updates Executorch Vulkan backend's `permute` operation to support width, height and channel packed tensors. It also updates the op_registry.py file to register the `permute` operation and adds a new test case to the cases.py file to test the operation. Additionally, it updates the Permute.cpp file to check for the same packed dimension in the input and output tensors, and updates the cases.py file to include the utils::kWidthPacked, utils::kHeightPacked, and utils::kChannelsPacked layouts. Reviewed By: SS-JIA Differential Revision: D70587814
trivedivivek
force-pushed
the
export-D70587814
branch
from
de14c21 to
ae230cd
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70587814 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D70587814 |
Summary: Pull Request resolved: pytorch#9215 This diff updates Executorch Vulkan backend's `permute` operation to support width, height and channel packed tensors. It also updates the op_registry.py file to register the `permute` operation and adds a new test case to the cases.py file to test the operation. Additionally, it updates the Permute.cpp file to check for the same packed dimension in the input and output tensors, and updates the cases.py file to include the utils::kWidthPacked, utils::kHeightPacked, and utils::kChannelsPacked layouts. Reviewed By: SS-JIA Differential Revision: D70587814
|
This pull request was exported from Phabricator. Differential Revision: D70587814 |
trivedivivek
force-pushed
the
export-D70587814
branch
from
ae230cd to
572a3dc
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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:
This diff updates Executorch Vulkan backend's
permuteoperation to support width, height and channel packed tensors.It also updates the op_registry.py file to register the
permuteoperation and adds a new test case to the cases.py file to test the operation.Additionally, it updates the Permute.cpp file to check for the same packed dimension in the input and output tensors, and updates the cases.py file to include the utils::kWidthPacked, utils::kHeightPacked, and utils::kChannelsPacked layouts.
Reviewed By: SS-JIA
Differential Revision: D70587814