EOL.Wiki EOL.Wiki
← ← Back to all products

PyTorch

Active
Frameworks Latest Version: 2.12.0 Latest Release: May 13, 2026

PyTorch is an open-source deep learning framework. Only the latest minor receives bug fixes and security patches, with no fixed EOL dates for older minors. PyTorch 2.12 requires Python 3.10+ and ships CUDA 12.6 / 13.0 wheels; 2.1-2.8 supported Python 3.8/3.9+ with CUDA 11.8/12.1.

Versions

12

Latest Version

2.12.0

Active Support

1

EOL

11

Lifecycle Timeline

Today
2.12
2.12
2.11
2.11
2.10
2.10
2.9
2.9
2.8
2.8
2.7
2.7
2.6
2.6
2.5
2.5
2.4
2.4
2.3
2.3
Active SupportSecurity SupportEOL

Versions

ReleaseRelease DateActive SupportEOLLatest VersionLTSStatus
2.12May 13, 2026YesNo2.12.0No
Active
2.11Mar 23, 2026NoYes2.11.0No
EOL
2.10Jan 21, 2026NoYes2.10.0No
EOL
2.9Oct 15, 2025NoYes2.9.1No
EOL
2.8Aug 6, 2025NoYes2.8.0No
EOL
2.7Apr 23, 2025NoYes2.7.1No
EOL
2.6Jan 29, 2025NoYes2.6.0No
EOL
2.5Oct 17, 2024NoYes2.5.1No
EOL
2.4Jul 24, 2024NoYes2.4.1No
EOL
2.3Apr 24, 2024NoYes2.3.1No
EOL
2.2Jan 30, 2024NoYes2.2.2No
EOL
2.1Oct 4, 2023NoYes2.1.2No
EOL

Frequently Asked Questions

Which versions of PyTorch have reached end of life?
The following PyTorch versions have reached end of life and no longer receive security updates: 2.11, 2.10, 2.9, 2.8, 2.7, 2.6, 2.5, 2.4 (and 3 more). It is recommended to upgrade to a supported version.
Is it safe to continue using PyTorch 2.11?
PyTorch 2.11 has reached end of life and no longer receives security patches or bug fixes. Continuing to use it may expose your systems to known vulnerabilities. We strongly recommend upgrading to a supported version.
What is the latest version of PyTorch?
The latest version of PyTorch is 2.12.0, released in the 2.12 release cycle.
How many versions of PyTorch are currently supported?
PyTorch currently has 1 actively supported version(s): 2.12.
When does PyTorch 2.12 reach end of life?
PyTorch 2.12 does not have a specific end-of-life date announced yet.
What should I do when PyTorch reaches end of life?
When a PyTorch version reaches end of life, you should: 1) Plan your migration to a supported version as soon as possible. 2) Review the release notes for breaking changes. 3) Test your applications thoroughly in a staging environment. 4) Update your dependencies to ensure compatibility with the new version.