Skip to content

Conversation

@codelion
Copy link
Member

  • Add support for mlx based inference on apple silicon devices

codelion added 5 commits June 17, 2025 16:00
This reverts commit 8287454.
Introduces a _robust_mlx_generate method that attempts MLX text generation using several parameter combinations to handle different MLX-LM versions. Improves error handling and logging for easier debugging, and ensures token counting is robust to different response types.
Update __version__ in optillm/__init__.py and version in setup.py to 0.1.16 for a new release.
@codelion codelion merged commit 2e4c0da into main Jun 24, 2025
1 check passed
@codelion codelion deleted the fix-bug-mps branch June 24, 2025 02:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants