cuda release on cpu-only machine

.circleci/config.yml

@@ -204,7 +204,7 @@ jobs:
 
   cuda_build_and_test:
     machine:
-      image: linux-cuda-12:2025.05.1
+      image: linux-cuda-12:2023.11.1
       resource_class: gpu.nvidia.small.gen2
     steps:
       - checkout
@@ -369,22 +369,27 @@ jobs:
         type: string
         default: ""
     machine:
-      image: linux-cuda-12:2024.11.1
-      resource_class: gpu.nvidia.small.gen2
+      image: ubuntu-2204:current
+      resource_class: large
     steps:
       - checkout
       - run:
           name: Build wheel
           command: |
+            export DEBIAN_FRONTEND=noninteractive
+            export NEEDRESTART_MODE=a
+            wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64/cuda-keyring_1.1-1_all.deb
+            sudo dpkg -i cuda-keyring_1.1-1_all.deb
             sudo apt-get update
+            sudo apt install cuda-toolkit-12-9
             sudo apt-get install libblas-dev liblapack-dev liblapacke-dev
             sudo apt-get install zip
-            python -m venv env
-            source env/bin/activate
             pip install auditwheel
             pip install patchelf
             pip install build
             pip install twine
+            export PATH=/usr/local/cuda/bin${PATH:+:${PATH}}
+            export LD_LIBRARY_PATH=/usr/local/cuda/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
             << parameters.build_env >> MLX_BUILD_STAGE=2 \
               CMAKE_ARGS="-DMLX_BUILD_CUDA=ON -DCMAKE_CUDA_COMPILER=`which nvcc`" \
               python -m build -w
@@ -395,7 +400,6 @@ jobs:
             - run:
                 name: Upload package
                 command: |
-                  source env/bin/activate
                   twine upload wheelhouse/*.whl
       - store_artifacts:
           path: wheelhouse/

python/scripts/repair_cuda.sh

@@ -4,6 +4,7 @@ auditwheel repair dist/* \
   --plat manylinux_2_35_x86_64 \
   --exclude libcublas* \
   --exclude libnvrtc* \
+  --exclude libcuda* \
   -w wheel_tmp
 
 

setup.py

@@ -295,5 +295,5 @@ if __name__ == "__main__":
         _setup(
             name=name,
             packages=["mlx"],
-            install_requires=install_requries,
+            install_requires=install_requires,
         )