From 996bdcecdcb22b78226e6584b2e6721a791f5961 Mon Sep 17 00:00:00 2001 From: localai-org-maint-bot Date: Tue, 28 Jul 2026 19:45:07 +0200 Subject: [PATCH] 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> --- backend/python/mlx-vlm/requirements-mps.txt | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/backend/python/mlx-vlm/requirements-mps.txt b/backend/python/mlx-vlm/requirements-mps.txt index 882c2af5a..ee5351beb 100644 --- a/backend/python/mlx-vlm/requirements-mps.txt +++ b/backend/python/mlx-vlm/requirements-mps.txt @@ -1 +1,3 @@ -git+https://github.com/Blaizzy/mlx-vlm@v0.4.4 \ No newline at end of file +git+https://github.com/Blaizzy/mlx-vlm@v0.4.4 +torch +torchvision