mirror of
https://github.com/deepspeedai/DeepSpeed.git
synced 2025-10-20 15:33:51 +08:00
b4cc079eee
these days fp16 is barely ever used, so we should be testing bf16 instead of fp16 where possible. had to fix a bunch of tests to adapt to this change. a few bugs as well on the way. --------- Signed-off-by: Stas Bekman <stas.bekman@snowflake.com> Co-authored-by: Olatunji Ruwase <tunji.ruwase@snowflake.com> Co-authored-by: Stas Bekman <stas.bekman@snowflake.com>
61 lines
1.8 KiB
YAML
61 lines
1.8 KiB
YAML
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, cu124, 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/cu124
|
|
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 981c276
|
|
git rev-parse --short HEAD
|
|
pip install .
|
|
|
|
- name: Install deepspeed
|
|
run: |
|
|
pip install .[dev,1bit,autotuning,deepcompile]
|
|
pip install pytest-timeout pytest-instafail
|
|
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 -x $PYTEST_OPTS --instafail --timeout 600 --forked -n 8 unit/ --torch_ver="2.6" --cuda_ver="12.4"
|
|
pytest $PYTEST_OPTS --instafail --timeout 600 --forked -m 'sequential' unit/ --torch_ver="2.6" --cuda_ver="12.4"
|