Skip to content

Add desktop README #15347

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
merged 2 commits into from
Oct 22, 2025
Merged

Add desktop README #15347

merged 2 commits into from
Oct 22, 2025
+25 −11

Conversation

mergennachin
Copy link
Contributor

No description provided.

@pytorch-bot
Copy link

pytorch-bot bot commented Oct 22, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15347

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

⏳ No Failures, 69 Pending

As of commit ad1fdcf with merge base 82611e9 (image):
💚 Looks good so far! There are no failures yet. 💚

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 22, 2025
@github-actions
Copy link

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.

larryliu0820
larryliu0820 reviewed Oct 22, 2025
View reviewed changes
desktop/README.md Outdated
- **No CUDA Support**: For a long time, ExecuTorch did not offer a CUDA backend, limiting GPU acceleration on NVIDIA hardware.

## Recent Developments
With increased demand for local inference on consumer desktops and laptops, exemplified by popular runtimes like llama.cpp and MLX, ExecuTorch is now experimenting with CUDA and Metal support. This is achieved by leveraging Inductor compiler technology from PyTorch, specifically using Ahead-of-Time Inductor (AOTI) to avoid reinventing the wheel.
Copy link
Contributor

Choose a reason for hiding this comment

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

Provide a link to AOTInudctor? https://docs.pytorch.org/docs/stable/torch.compiler_aot_inductor.html

larryliu0820
larryliu0820 reviewed Oct 22, 2025
View reviewed changes
desktop/README.md
- [CUDA backend](../backends/cuda)
- [Metal backend](../backends/apple/metal)

## Roadmap & Limitations
Copy link
Contributor

Choose a reason for hiding this comment

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

Mention that on windows we only supports WSL right now. Native Windows support is WIP

@mergennachin
Update README with AOTI documentation link
ad1fdcf 
Added a link to the AOTI documentation in the README.
@mergennachin mergennachin merged commit 259f1e6 into main Oct 22, 2025
121 of 125 checks passed
@mergennachin mergennachin deleted the mergennachin-patch-10 branch October 22, 2025 06:01
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

@manuelcandales manuelcandales Awaiting requested review from manuelcandales

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.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@mergennachin @larryliu0820