Daniel HiltgenandGitHub 2cd63f7a15 mlx: deduplicate CUDA runtime payloads (#17956) ...

* Deduplicate MLX CUDA runtime payloads

Move CUDA libraries shared by the GGML and MLX backends into the sibling CUDA payload, and teach in-process and subprocess MLX loading to resolve that packaged dependency directory.

Keep MLX-private libraries and JIT headers in the MLX overlay, include the full OpenBLAS Fortran runtime closure, and verify those dependencies in release packaging.

* address comments

2026-10-20 14:15:15 -07:00

..

CMakeLists.txt

mlx: deduplicate CUDA runtime payloads (#17956)

2026-10-20 14:15:15 -07:00

CMakePresets.json

mlx: enable CUDA backend in CUDA builds (#17688)

2026-08-12 07:31:00 -07:00