mirror of
https://github.com/deepspeedai/DeepSpeed.git
synced 2025-10-20 15:33:51 +08:00
aef6c65ce3
* add coverage report * define env vars in shared action * reduce time for longest running tests * fix broken shared action * reduce test time * reducing Pipeline test times * further reducing test times * rework Z3 test * testing new mp.pool and persistent dist envs * fix import * reuse distributed environment for tests with lots of param combos * fix for dist teardown * fix pickling issue with pool cache * actually fix pickling problem * avoid running pool cache stuff on non-distributed tests * fix issues with nested mp.pool * fix for nested pools in Pipeline Engine * re-add params * update workflows with pytest opts * implement feedback * resolve race condition with port selection * Update tests/unit/common.py --------- Co-authored-by: Olatunji Ruwase <olruwase@microsoft.com>
50 lines
1.4 KiB
YAML
50 lines
1.4 KiB
YAML
name: nv-torch19-p40
|
|
|
|
on:
|
|
schedule:
|
|
- cron: "0 0 * * *"
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
unit-tests:
|
|
runs-on: [self-hosted, nvidia, cu111, p40]
|
|
|
|
steps:
|
|
- uses: actions/checkout@v3
|
|
|
|
- id: setup-venv
|
|
uses: ./.github/workflows/setup-venv
|
|
|
|
- name: Install pytorch
|
|
run: |
|
|
pip install -U --cache-dir $TORCH_CACHE torch==1.9.0+cu111 torchvision==0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html
|
|
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 install .
|
|
|
|
- name: Install deepspeed
|
|
run: |
|
|
pip install .[dev,1bit,autotuning] --no-build-isolation
|
|
ds_report
|
|
|
|
- name: Python environment
|
|
run: |
|
|
pip list
|
|
|
|
- name: Unit tests
|
|
run: |
|
|
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
|
|
cd tests
|
|
pytest $PYTEST_OPTS --forked -n 4 unit/ --torch_ver="1.9" --cuda_ver="11.1"
|