0.45.3
📦 bitsandbytesView on GitHub →
✨ 1 features🐛 4 fixes🔧 2 symbols
Summary
This patch release introduces support for NVIDIA Blackwell GPUs via a new CUDA 12.8 build and includes several minor bug fixes.
✨ New Features
- Added CUDA 12.8 build supporting sm100 and sm120 targets for NVIDIA Blackwell GPUs.
🐛 Bug Fixes
- Fixed issue reported in #1490.
- Ensured create_dynamic_map always returns a float32 tensor.
- Corrected device placement for code tensor in QuantState.to().
- Updated CUDA versions displayed in error messages.
🔧 Affected Symbols
create_dynamic_mapQuantState.to