| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-08-16 | 1.2 kB | |
| v0.17.9 source code.tar.gz | 2026-08-16 | 5.7 MB | |
| v0.17.9 source code.zip | 2026-08-16 | 6.6 MB | |
| Totals: 3 Items | 12.3 MB | 2 | |
Security fix
- Fix RCE via insecure deserialization in checkpoint loading (GHSA-q85h-wmmp-59p8, high severity):
MultiNodeCheckpoint.load()calledtorch.load(..., weights_only=False)unconditionally when resuming training from a checkpoint directory. Because--model_resume_path(CLI) andLudwigModel.load(from_checkpoint=True)(public API) accept user-supplied paths with only an existence check, a craftedlatest.ckptcontaining a__reduce__gadget could execute arbitrary code. Fixed by settingweights_only=True, which uses PyTorch's restricted unpickler — sufficient for all standard optimizer (Adam, SGD) and scheduler state.
Bug fixes
- Fix Ray Data failing to read relative local paths:
read_remote_parquetnow resolves relative local paths to absolute before passing them to Ray Data. Ray 2.56+ schedules read tasks on remote workers whose working directory may differ from the driver, causing "no files found" errors for relative paths. - Fix lint errors from ruff 0.16.2 (RUF036): Move
Noneto the end of type unions across schema and utility files. - Remove broken star history chart embed from README (GitHub restricted stargazer API access on 2026-06-30).