Skip to content

FlatTensor alignment tests #16317

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.

Sign up for GitHub

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

Jump to bottom
Merged
meta-codesync merged 1 commit into from
Dec 22, 2025
Merged

FlatTensor alignment tests #16317

meta-codesync merged 1 commit into from
Dec 22, 2025

Conversation

@lucylq
Copy link
Contributor

@lucylq lucylq commented Dec 18, 2025

Summary:

  1. Pass segment_alignment from ExecutorchBackendConfig to flat tensor serializer
  2. Set segment_alignment=128 as default to match ExecutorchBackendConfig
  3. Remove tensor_alignment from the config (do not have multiple tensors per segment)
  4. Additional tests for varying segment alignment.

Differential Revision: D89422691

@pytorch-bot
Copy link

pytorch-bot bot commented Dec 18, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16317

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

✅ You can merge normally! (1 Unrelated Failure)

As of commit 049d87a with merge base 227ff2e (image):

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 meta-cla 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 Dec 18, 2025
@meta-codesync
Copy link

meta-codesync bot commented Dec 18, 2025

@lucylq has exported this pull request. If you are a Meta employee, you can view the originating Diff in D89422691.

@github-actions
Copy link

github-actions bot commented Dec 18, 2025

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

lucylq added a commit to lucylq/executorch-1 that referenced this pull request Dec 18, 2025
@lucylq @facebook-github-bot
FlatTensor alignment tests (pytorch#16317)
260adb2 
Summary:

1. Pass segment_alignment from ExecutorchBackendConfig to flat tensor serializer
2. Set segment_alignment=128 as default to match ExecutorchBackendConfig
3. Remove tensor_alignment from the config (do not have multiple tensors per segment)
4. Additional tests for varying segment alignment.

Differential Revision: D89422691
lucylq added a commit to lucylq/executorch-1 that referenced this pull request Dec 18, 2025
@lucylq @facebook-github-bot
FlatTensor alignment tests (pytorch#16317)
e334922 
Summary:

1. Pass segment_alignment from ExecutorchBackendConfig to flat tensor serializer
2. Set segment_alignment=128 as default to match ExecutorchBackendConfig
3. Remove tensor_alignment from the config (do not have multiple tensors per segment)
4. Additional tests for varying segment alignment.

Differential Revision: D89422691
larryliu0820
larryliu0820 approved these changes Dec 18, 2025
View reviewed changes
Copy link
Contributor

@larryliu0820 larryliu0820 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Review automatically exported from Phabricator review in Meta.

lucylq added a commit to lucylq/executorch-1 that referenced this pull request Dec 22, 2025
@lucylq @facebook-github-bot
FlatTensor alignment tests (pytorch#16317)
767d687 
Summary:

1. Pass segment_alignment from ExecutorchBackendConfig to flat tensor serializer

Other changes:
2. Set segment_alignment=128 as default to match ExecutorchBackendConfig
3. Remove tensor_alignment from the config (we do not have multiple tensors per segment anymore)
4. Set flatbuffer alignment=16. I don't think we need any alignment at the moment here, but can't hurt. The PTE file aligns flatbuffer to the largest force_align value in the schema, which the PTD file doesn't have.
5. Additional tests for varying segment alignment.

Reviewed By: larryliu0820

Differential Revision: D89422691
lucylq added a commit to lucylq/executorch-1 that referenced this pull request Dec 22, 2025
@lucylq @facebook-github-bot
FlatTensor alignment tests (pytorch#16317)
adebf53 
Summary:

1. Pass segment_alignment from ExecutorchBackendConfig to flat tensor serializer

Other changes:
2. Set segment_alignment=128 as default to match ExecutorchBackendConfig
3. Remove tensor_alignment from the config (we do not have multiple tensors per segment anymore)
4. Set flatbuffer alignment=16. I don't think we need any alignment at the moment here, but can't hurt. The PTE file aligns flatbuffer to the largest force_align value in the schema, which the PTD file doesn't have.
5. Additional tests for varying segment alignment.

Reviewed By: larryliu0820

Differential Revision: D89422691
lucylq added a commit to lucylq/executorch-1 that referenced this pull request Dec 22, 2025
@lucylq @facebook-github-bot
FlatTensor alignment tests (pytorch#16317)
5c9d110 
Summary:

1. Pass segment_alignment from ExecutorchBackendConfig to flat tensor serializer

Other changes:
2. Set segment_alignment=128 as default to match ExecutorchBackendConfig
3. Remove tensor_alignment from the config (we do not have multiple tensors per segment anymore)
4. Set flatbuffer alignment=16. I don't think we need any alignment at the moment here, but can't hurt. The PTE file aligns flatbuffer to the largest force_align value in the schema, which the PTD file doesn't have.
5. Additional tests for varying segment alignment.

Reviewed By: larryliu0820

Differential Revision: D89422691
lucylq added a commit to lucylq/executorch-1 that referenced this pull request Dec 22, 2025
@lucylq @facebook-github-bot
FlatTensor alignment tests (pytorch#16317)
bf7fc9e 
Summary:

1. Pass segment_alignment from ExecutorchBackendConfig to flat tensor serializer

Other changes:
2. Set segment_alignment=128 as default to match ExecutorchBackendConfig
3. Remove tensor_alignment from the config (we do not have multiple tensors per segment anymore)
4. Set flatbuffer alignment=16. I don't think we need any alignment at the moment here, but can't hurt. The PTE file aligns flatbuffer to the largest force_align value in the schema, which the PTD file doesn't have.
5. Additional tests for varying segment alignment.

Reviewed By: larryliu0820

Differential Revision: D89422691
@lucylq @facebook-github-bot
FlatTensor alignment tests (pytorch#16317)
049d87a 
Summary:

1. Pass segment_alignment from ExecutorchBackendConfig to flat tensor serializer

Other changes:
2. Set segment_alignment=128 as default to match ExecutorchBackendConfig
3. Remove tensor_alignment from the config (we do not have multiple tensors per segment anymore)
4. Set flatbuffer alignment=16. I don't think we need any alignment at the moment here, but can't hurt. The PTE file aligns flatbuffer to the largest force_align value in the schema, which the PTD file doesn't have.
5. Additional tests for varying segment alignment.

Reviewed By: larryliu0820

Differential Revision: D89422691
@meta-codesync meta-codesync bot merged commit 2abce02 into pytorch:main Dec 22, 2025
140 of 142 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@larryliu0820 larryliu0820 larryliu0820 approved these changes

@JacobSzwejbka JacobSzwejbka Awaiting requested review from JacobSzwejbka JacobSzwejbka is a code owner

Assignees

No one assigned

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported meta-exported

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@lucylq @larryliu0820