Skip to content

[wip]: chore/debug gpu tests #21290

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.

Sign up for GitHub

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

Draft
wants to merge 8 commits into
base: master
Choose a base branch
from
+10 −10
Draft

[wip]: chore/debug gpu tests #21290

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
ad3087f
fix: add unzip to dependencies in pytorch workflow
bhimrazy Oct 15, 2025
9441488
fix: update variable interpolation for PACKAGE_NAME in YAML workflows
bhimrazy Nov 2, 2025
3d363c0
fix: update variable interpolation for PACKAGE_NAME in fabric workflow
bhimrazy Nov 2, 2025
0d521d7
fix: disable CUDA_LAUNCH_BLOCKING to speed up tests
bhimrazy Nov 2, 2025
0403460
Merge branch 'master' into debug-gpu-tests
bhimrazy Nov 2, 2025
adb4338
apply suggestion
bhimrazy Nov 4, 2025
e24a8c2
Merge branch 'master' into debug-gpu-tests
bhimrazy Nov 4, 2025
35535d7
Merge branch 'master' into debug-gpu-tests
bhimrazy Nov 4, 2025
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
4 changes: 2 additions & 2 deletions .azure/gpu-tests-fabric.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ jobs:
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"
echo "##vso[task.setvariable variable=TORCH_URL]https://download.pytorch.org/whl/cu${cuda_ver}/torch_stable.html"
scope=$(python -c 'n = "$(PACKAGE_NAME)" ; print(dict(fabric="lightning_fabric").get(n, n))')
scope=$(python -c 'n = "${PACKAGE_NAME}" ; print(dict(fabric="lightning_fabric").get(n, n))')
echo "##vso[task.setvariable variable=COVERAGE_SOURCE]$scope"
displayName: "set env. vars"
- bash: |
Expand Down Expand Up @@ -140,7 +140,7 @@ jobs:

- bash: |
set -e
extra=$(python -c "print({'lightning': 'fabric-'}.get('$(PACKAGE_NAME)', ''))")
extra=$(python -c "print({'lightning': 'fabric-'}.get('${PACKAGE_NAME}', ''))")
pip install -e ".[${extra}dev]" -U --upgrade-strategy=eager --extra-index-url="${TORCH_URL}"
displayName: "Install package & dependencies"

Expand Down
4 changes: 2 additions & 2 deletions .azure/gpu-tests-pytorch.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ jobs:
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"
echo "##vso[task.setvariable variable=TORCH_URL]https://download.pytorch.org/whl/cu${cuda_ver}/torch_stable.html"
scope=$(python -c 'n = "$(PACKAGE_NAME)" ; print(dict(pytorch="pytorch_lightning").get(n, n))')
scope=$(python -c 'n = "${PACKAGE_NAME}" ; print(dict(pytorch="pytorch_lightning").get(n, n))')
echo "##vso[task.setvariable variable=COVERAGE_SOURCE]$scope"
displayName: "set env. vars"
- bash: |
Expand Down Expand Up @@ -139,7 +139,7 @@ jobs:

- bash: |
set -e
extra=$(python -c "print({'lightning': 'pytorch-'}.get('$(PACKAGE_NAME)', ''))")
extra=$(python -c "print({'lightning': 'pytorch-'}.get('${PACKAGE_NAME}', ''))")
pip install -e ".[${extra}dev]" -U --upgrade-strategy=eager --extra-index-url="${TORCH_URL}"
displayName: "Install package & dependencies"

Expand Down
4 changes: 2 additions & 2 deletions .lightning/workflows/fabric.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ run: |
CUDA_VERSION_M_M="${CUDA_VERSION%.*}" # "12.6"
CUDA_VERSION_MM="${CUDA_VERSION_M_M//./}" # "126"
export UV_TORCH_BACKEND=cu${CUDA_VERSION_MM}
COVERAGE_SOURCE=$(python -c 'n = "$(PACKAGE_NAME)" ; print(dict(fabric="lightning_fabric").get(n, n))')
COVERAGE_SOURCE=$(python -c 'n = "${PACKAGE_NAME}" ; print(dict(fabric="lightning_fabric").get(n, n))')
echo "collecting coverage for: ${COVERAGE_SOURCE}"

uv pip install fire wget packaging "lightning-utilities[cli]"
Expand Down Expand Up @@ -120,7 +120,7 @@ run: |
fi

echo "Install package with [${PACKAGE_NAME}] extras"
extra=$(python -c "print({'lightning': 'fabric-'}.get('$(PACKAGE_NAME)', ''))")
extra=$(python -c "print({'lightning': 'fabric-'}.get('${PACKAGE_NAME}', ''))")
uv pip install ".[${extra}dev]" --upgrade

python requirements/collect_env_details.py
Expand Down
8 changes: 4 additions & 4 deletions .lightning/workflows/pytorch.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,6 @@ env:
DEBIAN_FRONTEND: "noninteractive"
CUDA_TOOLKIT_ROOT_DIR: "/usr/local/cuda"
MKL_THREADING_LAYER: "GNU"
CUDA_LAUNCH_BLOCKING: "1"
NCCL_DEBUG: "INFO"
TORCHDYNAMO_VERBOSE: "1"
FREEZE_REQUIREMENTS: "1"
Expand All @@ -50,7 +49,8 @@ run: |
openmpi-bin \
ninja-build \
libnccl2 \
libnccl-dev
libnccl-dev \
unzip

echo "Install Python ${python_version} and UV"
apt-get install -y python${python_version} python${python_version}-venv python${python_version}-dev
Expand Down Expand Up @@ -85,7 +85,7 @@ run: |
CUDA_VERSION_M_M="${CUDA_VERSION%.*}" # "12.6"
CUDA_VERSION_MM="${CUDA_VERSION_M_M//./}" # "126"
export UV_TORCH_BACKEND=cu${CUDA_VERSION_MM}
COVERAGE_SOURCE=$(python -c 'n = "$(PACKAGE_NAME)" ; print(dict(fabric="pytorch_lightning").get(n, n))')
COVERAGE_SOURCE=$(python -c 'n = "${PACKAGE_NAME}" ; print(dict(fabric="pytorch_lightning").get(n, n))')
echo "collecting coverage for: ${COVERAGE_SOURCE}"

uv pip install -q fire wget packaging "lightning-utilities[cli]"
Expand Down Expand Up @@ -120,7 +120,7 @@ run: |
fi

echo "Install package"
extra=$(python -c "print({'lightning': 'pytorch-'}.get('$(PACKAGE_NAME)', ''))")
extra=$(python -c "print({'lightning': 'pytorch-'}.get('${PACKAGE_NAME}', ''))")
uv pip install -e ".[${extra}dev]" --upgrade

echo "Ensure only a single package is installed"
Expand Down