Skip to content

nv-transformers-v100 #135

nv-transformers-v100

nv-transformers-v100 #135

name: nv-transformers-v100
on:
pull_request:
paths-ignore:
- 'docs/**'
- 'blogs/**'
- 'deepspeed/inference/v2/**'
- 'tests/unit/inference/v2/**'
merge_group:
branches: [ master ]
schedule:
- cron: "0 0 * * *"
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu117, v100]
steps:
- uses: actions/checkout@v4
- id: setup-venv
uses: ./.github/workflows/setup-venv
- name: Install pytorch
run: |
# use the same pytorch version as transformers CI
pip install -U --cache-dir $TORCH_CACHE torch==2.0.1+cu118 --index-url https://download.pytorch.org/whl/cu118
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 e7e9261a2
git rev-parse --short HEAD
pip install .
- name: Install deepspeed
run: |
pip install .[dev,autotuning]
ds_report
- name: Python environment
run: |
pip list
- name: HF transformers tests
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd transformers
pip install .[testing]
# find reqs used in ds integration tests
find examples/pytorch -regextype posix-egrep -regex '.*(language-modeling|question-answering|summarization|image-classification|text-classification|translation).*/requirements.txt' -exec grep -v 'torch' {} \; | xargs -I {} pip install --upgrade {}
# force protobuf version due to issues
pip install "protobuf<4.21.0"
pip list
WANDB_DISABLED=true RUN_SLOW=1 pytest $PYTEST_OPTS tests/deepspeed