mirror of
https://github.com/ollama/ollama.git
synced 2026-04-18 08:54:13 +02:00
c2b0bb7a52
* mlx: update to HEAD on 3/23 Also fixes a few misc vendoring bugs uncovered with this first update. This also renames the version files to make them clearer. * CUDA Fast Gated Delta kernel * mlx: detect eval errors and panic On model errors or missing kernels, don't mask the error, bubble it up.
Vendored MLX-C Headers
These header files are vendored from mlx-c.
The pinned version is in MLX_C_VERSION at the repo root.
Headers are automatically refreshed when you run a CMake build:
cmake --preset 'MLX CUDA 13'
See the MLX Engine section of the development docs for full build instructions.