Skip to content

nv-torch-latest-v100 #12734

nv-torch-latest-v100

nv-torch-latest-v100 #12734

name: nv-torch-latest-v100
on:
workflow_dispatch:
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, cu121, v100]
steps:
- uses: actions/checkout@v4
- id: setup-venv
uses: ./.github/workflows/setup-venv
- name: Install pytorch
run: |
pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
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 6c3f168b3
git rev-parse --short HEAD
pip install .
- name: Install deepspeed
run: |
pip install .[dev,1bit,autotuning]
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="2.5" --cuda_ver="12.1"
pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="2.5" --cuda_ver="12.1"