LocalAI

mirror of https://github.com/mudler/LocalAI.git synced 2026-07-30 18:09:05 -04:00

Files

localai-org-maint-bot 996bdcecdc fix(mlx-vlm): install torch dependencies on Metal (#11164 )

Some Transformers processors used by MLX-VLM, including Qwen vision models, import both PyTorch and Torchvision. Include them in the Metal backend environment so model loading does not fail with missing-library errors.

Assisted-by: Codex:gpt-5

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>

2026-07-28 19:45:07 +02:00

backend.py

feat: refactor shared helpers and enhance MLX backend functionality (#9335 )

2026-04-13 18:44:03 +02:00

install.sh

Add mlx-vlm (#6119 )

2025-08-23 23:05:30 +02:00

Makefile

Add mlx-vlm (#6119 )

2025-08-23 23:05:30 +02:00

requirements-cpu.txt

fix(mlx-vlm): pin upstream to v0.4.4 to unblock CUDA builds (#9568 )