v4.51.3
📦 transformersView on GitHub →
✨ 1 features🐛 2 fixes🔧 2 symbols
Summary
This patch release introduces support for the GLM-4 model and includes several fixes for PyTorch version compatibility, specifically regarding FlexAttention.
✨ New Features
- Added support for GLM-4 model architecture.
🐛 Bug Fixes
- Improved handling of torch versioning within FlexAttention.
- Fixed edge cases related to torch version detection.
🔧 Affected Symbols
GLM4flexattn