[ET-VK][ez] Restrict batch norm operator to 4D input tensors only #16420
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
Batch normalization is typically used with 4D tensors (batch, channels, height, width) in convolutional neural networks. This change adds input validation to ensure batch norm is only lowered to the Vulkan backend when the input tensor is 4-dimensional. For other input shapes, the operator will fall back to other backends. The implementation follows the same pattern as the convolution operator, using an `are_node_inputs_supported_fn` callback to validate input shapes during graph partitioning. This prevents potential issues with batch norm on unsupported tensor shapes and makes the operator requirements explicit. Differential Revision: [D89935219](https://our.internmc.facebook.com/intern/diff/D89935219/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Dec 30, 2025
Batch normalization is typically used with 4D tensors (batch, channels, height, width) in convolutional neural networks. This change adds input validation to ensure batch norm is only lowered to the Vulkan backend when the input tensor is 4-dimensional. For other input shapes, the operator will fall back to other backends. The implementation follows the same pattern as the convolution operator, using an `are_node_inputs_supported_fn` callback to validate input shapes during graph partitioning. This prevents potential issues with batch norm on unsupported tensor shapes and makes the operator requirements explicit. Differential Revision: [D89935219](https://our.internmc.facebook.com/intern/diff/D89935219/) ghstack-source-id: 331442243 Pull Request resolved: #16420
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16420
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 2 New Failures, 1 Unrelated FailureAs of commit c82b24b with merge base 1066e7c ( NEW FAILURES - The following jobs have failed:
UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
…rs only" Batch normalization is typically used with 4D tensors (batch, channels, height, width) in convolutional neural networks. This change adds input validation to ensure batch norm is only lowered to the Vulkan backend when the input tensor is 4-dimensional. For other input shapes, the operator will fall back to other backends. The implementation follows the same pattern as the convolution operator, using an `are_node_inputs_supported_fn` callback to validate input shapes during graph partitioning. This prevents potential issues with batch norm on unsupported tensor shapes and makes the operator requirements explicit. Differential Revision: [D89935219](https://our.internmc.facebook.com/intern/diff/D89935219/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Dec 30, 2025
Pull Request resolved: #16420 Batch normalization is typically used with 4D tensors (batch, channels, height, width) in convolutional neural networks. This change adds input validation to ensure batch norm is only lowered to the Vulkan backend when the input tensor is 4-dimensional. For other input shapes, the operator will fall back to other backends. The implementation follows the same pattern as the convolution operator, using an `are_node_inputs_supported_fn` callback to validate input shapes during graph partitioning. This prevents potential issues with batch norm on unsupported tensor shapes and makes the operator requirements explicit. ghstack-source-id: 331443282 @exported-using-ghexport Differential Revision: [D89935219](https://our.internmc.facebook.com/intern/diff/D89935219/)
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.
Stack from ghstack (oldest at bottom):
Batch normalization is typically used with 4D tensors (batch, channels, height, width) in convolutional neural networks. This change adds input validation to ensure batch norm is only lowered to the Vulkan backend when the input tensor is 4-dimensional. For other input shapes, the operator will fall back to other backends.
The implementation follows the same pattern as the convolution operator, using an
are_node_inputs_supported_fncallback to validate input shapes during graph partitioning. This prevents potential issues with batch norm on unsupported tensor shapes and makes the operator requirements explicit.Differential Revision: D89935219