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)

2026-04-25 22:06:01 +02:00

requirements-cublas12.txt

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

2026-04-25 22:06:01 +02:00

requirements-cublas13.txt

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

2026-04-25 22:06:01 +02:00

requirements-l4t12.txt

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

2026-04-25 22:06:01 +02:00

requirements-l4t13.txt

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

2026-04-25 22:06:01 +02:00

requirements-mps.txt

fix(mlx-vlm): install torch dependencies on Metal (#11164)

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

requirements.txt

Add mlx-vlm (#6119)

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

run.sh

Add mlx-vlm (#6119)

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

test.py

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

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

test.sh

Add mlx-vlm (#6119)

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