Skip to content

Conversation

GregoryComer
Copy link
Member

@GregoryComer GregoryComer commented Oct 8, 2025

Summary

Prototype an updated doc structure for the XNNPACK backend. Extract a common template out under docs/source/backends/tempate/

This PR updates the doc structure as follows. Under the template, the landing page is required, partitioner, quantization, and op support docs are recommended, and the rest are optional.

  • XNNPACK Backend
    • Quantization (recommended)
    • Partitioner APIs (recommended)
    • Operator Support (optional)
    • Architecture and Internals (optional)
    • Tutorials (optional)
    • Guides (optional)

Copy link

pytorch-bot bot commented Oct 8, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14873

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

❌ 4 New Failures, 3 Pending

As of commit 592f698 with merge base 019c8da (image):

NEW FAILURES - The following jobs have 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 Oct 8, 2025
Copy link

github-actions bot commented Oct 8, 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.

@GregoryComer
Copy link
Member Author

This is a pretty early draft, but I'd be interested in any thoughts.
https://docs-preview.pytorch.org/pytorch/executorch/14873/backends/xnnpack/xnnpack-overview.html

CC @digantdesai @psiddh @mergennachin @cccclai @metascroy

@GregoryComer GregoryComer force-pushed the new-backend-docs branch 3 times, most recently from 15169b1 to bd30b09 Compare October 8, 2025 22:00
@GregoryComer GregoryComer changed the title [WIP] Prototype updated XNNPACK doc structure [WIP] Update XNNPACK doc structure Oct 8, 2025
@GregoryComer GregoryComer changed the title [WIP] Update XNNPACK doc structure Update XNNPACK doc structure and add template Oct 9, 2025
@GregoryComer GregoryComer marked this pull request as ready for review October 9, 2025 07:21
| Backend | Platform(s) | Hardware Type | Typical Use Case |
|-----------------------------------------------|---------------------|---------------|---------------------------------|
| [XNNPACK](backends/xnnpack/xnnpack-overview) | All | CPU | General-purpose, fallback |
| [Core ML](backends-coreml) | iOS, macOS | NPU/GPU | Apple devices, high performance |
Copy link
Contributor

Choose a reason for hiding this comment

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

CoreML is CPU too

Copy link
Contributor

@digantdesai digantdesai left a comment

Choose a reason for hiding this comment

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

LGTM, left some comments.

@@ -0,0 +1,3 @@
# Using {FEATURE} on {BACKEND_NAME}

This is a placeholder guide.
Copy link
Contributor

Choose a reason for hiding this comment

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

Can we add meta details about the intended use of this section?


## Step 1: Environment Setup

This tutorial is intended to be run from a {SUPPORTED_HOST_OS} and uses Conda for Python environment management. For full setup details and system requirements, see [Getting Started with ExecuTorch](/getting-started).
Copy link
Contributor

Choose a reason for hiding this comment

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

+1

@metascroy metascroy mentioned this pull request Oct 11, 2025
:hidden:
:caption: {BACKEND} Backend
backend-troubleshooting
Copy link
Contributor

Choose a reason for hiding this comment

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

np: do you wanna put the troubleshooting section a bit further back in the list?

Copy link
Contributor

Choose a reason for hiding this comment

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

I think we went back and forth (literally on the list too :p)

backend-troubleshooting
backend-partitioner
backend-quantization
backend-op-support
Copy link
Contributor

Choose a reason for hiding this comment

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

thinking more, technically op-support can be under partitioner.

So thinking out loud,

  • partitioner, quantizer (two entry point, separate pages)
  • tutorials (curious why it is not here?)
  • internals (can also house reference material facts which can't be part of parishioner or quantizer)
  • guide/troubleshooting/gotcha/faq (one page with a title reflecting it is for all these :p)

@mergennachin
Copy link
Contributor

@GregoryComer @digantdesai

Under Edge Platforms (iOS, Android, Desktop, C++) etc

I don't see XNNPACK anymore on the left nav "Edge->Android->Backends", as well as the overview page

https://docs-preview.pytorch.org/pytorch/executorch/14873/android-backends.html (no link to XNNPACK)

https://docs-preview.pytorch.org/pytorch/executorch/14873/android-section.html (no XNNPACK on left nav)

SS-JIA added a commit that referenced this pull request Oct 14, 2025
Summary:
Title says it all!

Add docs for the Samsung backend based on the template introduced in #14873.
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.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants