Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Install colossalai==0.1.12 in CI #16587

Merged
merged 5 commits into from
Feb 1, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions .azure/gpu-tests-pytorch.yml
Original file line number Diff line number Diff line change
Expand Up @@ -67,12 +67,15 @@ jobs:
echo "##vso[task.setvariable variable=CUDA_VISIBLE_DEVICES]$(DEVICES)"
cuda_ver=$(python -c "import torch ; print(''.join(map(str, torch.version.cuda.split('.')[:2])))")
echo "##vso[task.setvariable variable=CUDA_VERSION_MM]$cuda_ver"
pytorch_ver=$(python -c "import torch; print(torch.__version__.split('+')[0][:4])")
echo "##vso[task.setvariable variable=PYTORCH_VERSION]$pytorch_ver"
echo "##vso[task.setvariable variable=TORCH_URL]https://download.pytorch.org/whl/cu${cuda_ver}/torch_stable.html"
displayName: 'set env. vars'

- bash: |
echo $CUDA_VISIBLE_DEVICES
echo $CUDA_VERSION_MM
echo $PYTORCH_VERSION
echo $TORCH_URL
lspci | egrep 'VGA|3D'
whereis nvidia
Expand All @@ -84,7 +87,6 @@ jobs:
displayName: 'Image info & NVIDIA'

- bash: |
PYTORCH_VERSION=$(python -c "import torch; print(torch.__version__.split('+')[0])")
for fpath in `ls requirements/**/*.txt`; do \
python ./requirements/pytorch/adjust-versions.py $fpath ${PYTORCH_VERSION}; \
done
Expand All @@ -105,10 +107,9 @@ jobs:
CUDA_VERSION_BAGUA=$(python -c "print([ver for ver in [116,113,111,102] if $CUDA_VERSION_MM >= ver][0])")
pip install "bagua-cuda$CUDA_VERSION_BAGUA"

PYTORCH_VERSION_COLOSSALAI=$(python -c "import torch; print(torch.__version__.split('+')[0][:4])")
CUDA_VERSION_MM_COLOSSALAI=$(python -c "import torch ; print(''.join(map(str, torch.version.cuda)))")
CUDA_VERSION_COLOSSALAI=$(python -c "print([ver for ver in [11.3, 11.1] if $CUDA_VERSION_MM_COLOSSALAI >= ver][0])")
pip install "colossalai==0.1.10+torch${PYTORCH_VERSION_COLOSSALAI}cu${CUDA_VERSION_COLOSSALAI}" --find-links https://release.colossalai.org
pip install "colossalai==0.1.12+torch${PYTORCH_VERSION}cu${CUDA_VERSION_COLOSSALAI}" --find-links https://release.colossalai.org

pip install -r requirements/pytorch/strategies.txt --find-links ${TORCH_URL}

Expand Down
3 changes: 1 addition & 2 deletions dockers/base-cuda/Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -115,10 +115,9 @@ RUN \
# install ColossalAI
# TODO: 1.13 wheels are not released, remove skip once they are
if [[ $PYTORCH_VERSION != "1.13" ]]; then \
PYTORCH_VERSION_COLOSSALAI=$(python -c "import torch; print(torch.__version__.split('+')[0][:4])") ; \
CUDA_VERSION_MM_COLOSSALAI=$(python -c "import torch ; print(''.join(map(str, torch.version.cuda)))") ; \
CUDA_VERSION_COLOSSALAI=$(python -c "print([ver for ver in [11.3, 11.1] if $CUDA_VERSION_MM_COLOSSALAI >= ver][0])") ; \
pip install "colossalai==0.1.10+torch${PYTORCH_VERSION_COLOSSALAI}cu${CUDA_VERSION_COLOSSALAI}" --find-links https://release.colossalai.org ; \
pip install "colossalai==0.1.12+torch${PYTORCH_VERSION}cu${CUDA_VERSION_COLOSSALAI}" --find-links https://release.colossalai.org ; \
python -c "import colossalai; print(colossalai.__version__)" ; \
fi

Expand Down
2 changes: 0 additions & 2 deletions requirements/pytorch/strategies.txt
Original file line number Diff line number Diff line change
@@ -1,5 +1,3 @@
# NOTE: the upper bound for the package version is only set for CI stability, and it is dropped while installing this package
# in case you want to preserve/enforce restrictions on the latest compatible version, add "strict" as an in-line comment

# colossalai>=0.1.10 # TODO: uncomment when there's a stable version released
carmocca marked this conversation as resolved.
Show resolved Hide resolved
deepspeed>=0.6.0, <=0.7.0