public
/
nixpkgs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

pytorch: Move cudatoolkit to nativeBuildInputs 

nvcc must be available in PATH at build time; otherwise CUDA support
will be disabled.

Signed-off-by: Anders Kaseorg <andersk@mit.edu>
This commit is contained in:
Anders Kaseorg 2019-04-21 19:31:55 -07:00 committed by Frederik Rietdijk
parent a416ef58b7
commit 27d13628ee
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
pkgs/development/python-modules/pytorch/default.nix
View File

@ -81,11 +81,11 @@ in buildPythonPackage rec {
cmake cmake
utillinux utillinux
which which
]; ] ++ lib.optionals cudaSupport [ cudatoolkit_joined ];
buildInputs = [ buildInputs = [
numpy.blas numpy.blas
] ++ lib.optionals cudaSupport [ cudatoolkit_joined cudnn ] ] ++ lib.optionals cudaSupport [ cudnn ]
++ lib.optionals stdenv.isLinux [ numactl ]; ++ lib.optionals stdenv.isLinux [ numactl ];
propagatedBuildInputs = [ propagatedBuildInputs = [