[Gasoonjia]

Summary

Use the merged conda bootstrap repair from pytorch/test-infra#9179 by pinning only the Windows CUDA wheel build helper checkout to e3d344d886a7281f6a919115d332df2a080da8ad. It avoids installing conda=25.3.0 into the old Windows runner base environment and uses the runner's existing conda to create the isolated build environment. The reusable workflow, CUDA matrix generation, and ExecuTorch checkout remain unchanged. No failures are ignored and no tests are disabled.

Keep the immutable helper pin while validating this repair on ExecuTorch. Evaluate returning the helper ref to main after real CI validates the merged repair.

Failure And Iteration

On October 22, every Windows CUDA wheel build in https://github.com/pytorch/executorch/actions/runs/39755980076 failed before compilation during conda install -y conda=25.3.0. Upload, bundle, and Windows E2E failures followed because no wheel artifact was produced. The October 21 nightly was green: https://github.com/pytorch/executorch/actions/runs/39593845176.

The first version of this PR pinned the proposed Python 3.11 bootstrap repair from upstream #9177. Real CI https://github.com/pytorch/executorch/actions/runs/39860577061 proved that conda install -y python=3.11 conda=25.3.0 still fails with UnsatisfiableError, including historical base-environment package constraints such as menuinst. The CUDA 13.2 program export succeeded, but the wheel build failed in shared bootstrap before compilation. This revision adopts the merged #9179 repair, which removes that base-environment installation entirely.

Validation

Actionlint 1.7.12 passes. YAML parses and structural equality assertions verify that only the build helper ref changes; matrix generation, ExecuTorch checkout, and all test jobs are unchanged.

Real Windows CUDA wheel validation is pending for head 65236798ff45d18e0c22e88e7268b31d51a47fd9. First require the PR's Python 3.11/CUDA 13.2 build, smoke, upload, bundle, and Windows GPU E2E to execute and succeed. Then dispatch the full Python 3.11-3.15/CUDA 13.2 and 13.4 matrix and require all ten wheel builds/uploads and both GPU E2E paths to execute and succeed.

This PR remains draft until validation completes. Authored with AI assistance using Devmate.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24099

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit 7bf8122 with merge base 71a713c ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[linux-foundation-easycla]

The committers listed above are authorized under a signed CLA.

• ✅ login: Gasoonjia / name: gasoonjia (54f0056, 7bf8122)

[github-actions]

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.