pytorch/scripts/release
Eli Uriegas 07ae4e9309 scripts: Add script to prep wheels for pypi (#53056)
Summary:
Adds a script so that we can take wheels directly from
download.pytorch.org and publish them to pypi

This is currently mainly used to prep windows binaries for publication to PyPI

Signed-off-by: Eli Uriegas <eliuriegas@fb.com>

Pull Request resolved: https://github.com/pytorch/pytorch/pull/53056

Reviewed By: H-Huang

Differential Revision: D26738642

Pulled By: seemethere

fbshipit-source-id: 96777ed6c3f3454bddb4bc13121f727074312816
2021-03-01 16:46:44 -08:00
..
anaconda-prune
promote scripts: Add script to prep wheels for pypi (#53056) 2021-03-01 16:46:44 -08:00
README.md
restore-backup.sh

PyTorch Release Scripts

These are a collection of scripts that are to be used for release activities.

NOTE: All scripts should do no actual work unless the DRY_RUN environment variable is set to disabled. The basic idea being that there should be no potential to do anything dangerous unless DRY_RUN is explicitly set to disabled.

Requirements to actually run these scripts

  • AWS access to pytorch account
  • Access to upload conda packages to the pytorch conda channel
  • Access to the PyPI repositories

Promote

These are scripts related to promotion of release candidates to GA channels, these can actually be used to promote pytorch, libtorch, and related domain libraries.

Usage

Usage should be fairly straightforward and should actually require no extra variables if you are running from the correct git tags. (i.e. the GA tag to promote is currently checked out)

PACKAGE_TYPE and PACKAGE_NAME can be swapped out to promote other packages.

Promoting pytorch wheels

promote/s3_to_s3.sh

Promoting libtorch archives

PACKAGE_TYPE=libtorch PACKAGE_NAME=libtorch promote/s3_to_s3.sh

Promoting conda packages

promote/conda_to_conda.sh

Promoting wheels to PyPI

WARNING: These can only be run once and cannot be undone, run with caution

promote/wheel_to_pypi.sh

Restoring backups

All release candidates are currently backed up to s3://pytorch-backup/${TAG_NAME} and can be restored to the test channels with the restore-backup.sh script.

Which backup to restore from is dictated by the RESTORE_FROM environment variable.

Usage

RESTORE_FROM=v1.5.0-rc5 ./restore-backup.sh