Skip to content

Copy slice-scatter inputs into channels-packed textures - #24438

Open
JakeStevens wants to merge 2 commits into
pytorch:mainfrom
JakeStevens:export-D129088172
Open

JakeStevens wants to merge 2 commits into
pytorch:mainfrom
JakeStevens:export-D129088172

Conversation

@JakeStevens

Copy link
Copy Markdown
Contributor

Summary:

Ulterior Motive

Unblock Swin V2's runtime query/key/value bias update.

Rationale

What: Copy and repack slice_scatter inputs and output in the kernel's required channels-packed texture representation.

Why: The stored bias is cloned and updated at runtime, but its planned buffers do not satisfy the operator's texture-only contract.

Details

  • Repack self and src only when they are not standard channels-packed textures.
  • Reject over-limit tensors before constructing temporary tensors.
  • Dispatch into a matching temporary and copy back when the planned output differs.

Authored with AI using Metamate on agentcloud.

Differential Revision: D129088172

Summary:

Originally, the example supported only mv2.

This PR extends that support to all models within torchvision.

to be more specific, it allows you to export any torchvision model via a script-- it does *not* imply all export successfully or will run successfully. These will be addressed in follow-on PRs.

Reviewed By: SS-JIA

Differential Revision: D128684681
Summary:
## Ulterior Motive

Unblock Swin V2's runtime query/key/value bias update.

## Rationale

**What**: Copy and repack `slice_scatter` inputs and output in the kernel's required channels-packed texture representation.

**Why**: The stored bias is cloned and updated at runtime, but its planned buffers do not satisfy the operator's texture-only contract.

## Details

- Repack `self` and `src` only when they are not standard channels-packed textures.
- Reject over-limit tensors before constructing temporary tensors.
- Dispatch into a matching temporary and copy back when the planned output differs.

Authored with AI using Metamate on agentcloud.

Differential Revision: D129088172
@pytorch-bot

pytorch-bot Bot commented Nov 2, 2026 •

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24438

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

❌ 1 New Failure

As of commit 8fa8785 with merge base cec2e73 (image):

NEW FAILURE - The following job has failed:

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 Nov 2, 2026
@meta-codesync

meta-codesync Bot commented Nov 2, 2026

Copy link
Copy Markdown
Contributor

@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D129088172.

@github-actions

github-actions Bot commented Nov 2, 2026

Copy link
Copy Markdown

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.

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

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

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant