Files
DeepSpeed/.github/workflows/nv-torch-nightly-v100.yml
2022-06-15 14:21:19 -07:00

58 lines
1.8 KiB
YAML

name: nv-torch-nightly-v100
on:
schedule:
- cron: "0 0 * * *"
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu113, v100]
steps:
- uses: actions/checkout@v2
- name: environment
run: |
nvidia-smi
which python
python --version
which nvcc
nvcc --version
pip install --upgrade pip
pip uninstall --yes torch torchvision
pip install --pre torch torchvision --extra-index-url https://download.pytorch.org/whl/nightly/cu113
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
- name: Install transformers
run: |
git clone https://github.com/huggingface/transformers
cd transformers
# if needed switch to the last known good SHA until transformers@master is fixed
# git checkout 1cc453d33
git rev-parse --short HEAD
pip uninstall --yes transformers
pip install .
- name: Python environment
run: |
pip list
- name: Install deepspeed
run: |
pip uninstall --yes deepspeed
pip install .[dev,1bit,autotuning,sparse_attn]
ds_report
- name: Unit tests
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
if [[ -d ./torch-extensions ]]; then rm -rf ./torch-extensions; fi
cd tests
TORCH_EXTENSIONS_DIR=./torch-extensions pytest --color=yes --durations=0 --forked --verbose -n 4 unit/
TORCH_EXTENSIONS_DIR=./torch-extensions pytest --color=yes --durations=0 --forked --verbose -m 'sequential' unit/