| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-07-05 | 1.0 kB | |
| v0.3.19 source code.tar.gz | 2026-07-05 | 1.3 MB | |
| v0.3.19 source code.zip | 2026-07-05 | 1.5 MB | |
| Totals: 3 Items | 2.8 MB | 0 | |
What's Changed
Fix: import optillm crash on macOS with transformers 5.13 (#316)
A fresh install on Apple silicon crashed with AttributeError: 'str' object has no attribute '__module__' at import optillm.
- Root cause: transformers 5.13.0 tightened
AutoTokenizer.register()to require a class, butmlx-lm0.31.3 registers a custom tokenizer by string name (tokenizer_utils.py: AutoTokenizer.register("NewlineTokenizer", ...)). transformers ≤5.12.1 tolerated it. - macOS-only: optillm installs
mlx-lmonly on Apple silicon (platform_machine=="arm64" and sys_platform=="darwin"); Linux CI never installs it, so CI was unaffected. - Fix: pin
transformers>=5.0.0,<5.13.0(resolves to 5.12.1). The transformers 5.13.0 HF path itself is fine (dhara loads and generates); the incompatibility is purely mlx-lm's. Lift the cap once mlx-lm ships a transformers-5.13-compatible release.
Full Changelog: https://github.com/algorithmicsuperintelligence/optillm/compare/v0.3.18...v0.3.19