Skip to content

Commit 7bcaa73

Browse files
arai713illsilin
authored andcommitted
[rocm-libraries] ROCm/rocm-libraries#6537 (commit 16be4f7)
[CK] Fix for hipblaslt error in PyTorch Dockerfile ## Motivation This PR fixes the hipblaslt client build failures that occur when building the PyTorch Docker image, which are currently causing failures in CI. ## Technical Details - Correctly reset the working directory to tmp/ - Added --use-system-packages to the install.sh to use system installed laplack packages, as hard-coded paths were not being built. ## Test Plan Locally built the Docker image using the Dockerfile. ## Test Result Image was successfully built. ## Submission Checklist - [x] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests. Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
1 parent d22aafb commit 7bcaa73

1 file changed

Lines changed: 2 additions & 1 deletion

File tree

Dockerfile.pytorch

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,11 +22,12 @@ RUN groupadd -g 109 render && \
2222
chmod -R a+rwx /tmp/pytorch && \
2323
sudo usermod -aG irc jenkins && \
2424
#install hipblaslt
25+
cd /tmp && \
2526
git clone --no-checkout --filter=blob:none https://github.com/ROCm/rocm-libraries.git && \
2627
cd rocm-libraries && \
2728
git checkout develop && \
2829
git sparse-checkout init --cone && \
2930
git sparse-checkout set projects/hipblaslt shared/origami && \
3031
cd projects/hipblaslt && \
3132
git show --oneline -s && \
32-
CPLUS_INCLUDE_PATH="/opt/amdgpu/include/" ./install.sh -idc --architecture="gfx942;gfx950" -j 128 --skip_rocroller
33+
CPLUS_INCLUDE_PATH="/opt/amdgpu/include/" ./install.sh -idc --use-system-packages --architecture="gfx942;gfx950" -j 128 --skip_rocroller

0 commit comments

Comments
 (0)