xpu-max1100 #138
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: xpu-max1100 | |
on: | |
workflow_dispatch: | |
schedule: | |
- cron: "0 0 * * *" | |
pull_request: | |
paths: | |
- ".github/workflows/xpu-max1100.yml" | |
- "accelerator/xpu_accelerator.py" | |
- "accelerator/abstract_accelerator.py" | |
- "accelerator/cpu_accelerator.py" | |
- "accelerator/real_accelerator.py" | |
- "csrc/xpu/**" | |
- "deepspeed/runtime/engine.py" | |
- "deepspeed/runtime/bf16_optimizer.py" | |
- "deepspeed/runtime/zero/stage_1_and_2.py" | |
- "deepspeed/runtime/zero/stage3.py" | |
- "deepspeed/runtime/zero/partition_parameters.py" | |
- "deepspeed/runtime/zero/partitioned_param_coordinator.py" | |
- "deepspeed/runtime/zero/parameter_offload.py" | |
- "deepspeed/runtime/pipe/engine.py" | |
- "deepspeed/runtime/utils.py" | |
- "opbuilder/xpu/**" | |
concurrency: | |
group: ${{ github.workflow }}-${{ github.ref }} | |
cancel-in-progress: true | |
permissions: | |
contents: read | |
issues: write | |
jobs: | |
unit-tests: | |
runs-on: [self-hosted, intel, xpu] | |
container: | |
image: intel/intel-extension-for-pytorch:2.1.30-xpu | |
ports: | |
- 80 | |
options: --privileged -it --rm --device /dev/dri:/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --ipc=host --cap-add=ALL | |
steps: | |
- uses: actions/checkout@v4 | |
- name: Check container state | |
shell: bash | |
run: | | |
ldd --version | |
python -c "import torch; print('torch:', torch.__version__, torch)" | |
python -c "import torch; import intel_extension_for_pytorch; print('XPU available:', torch.xpu.is_available())" | |
- name: Install deepspeed | |
run: | | |
pip install py-cpuinfo | |
pip install .[dev,autotuning] | |
ds_report | |
python -c "from deepspeed.accelerator import get_accelerator; print('accelerator:', get_accelerator()._name)" | |
- name: Python environment | |
run: | | |
pip list | |
- name: Unit tests | |
run: | | |
pip install pytest pytest-timeout tabulate tensorboard wandb | |
export ONEAPI_ROOT=/opt/intel/oneapi/redist | |
export FI_PROVIDER_PATH=$ONEAPI_ROOT/opt/mpi/libfabric/lib/prov | |
export LD_LIBRARY_PATH=$ONEAPI_ROOT/opt/mpi/libfabric/lib:$LD_LIBRARY_PATH | |
export LD_LIBRARY_PATH=$ONEAPI_ROOT/lib:$LD_LIBRARY_PATH | |
cd tests/unit | |
pytest --verbose accelerator/* | |
pytest --verbose autotuning/* | |
pytest --verbose checkpoint/test_reshape_checkpoint.py | |
pytest --verbose checkpoint/test_moe_checkpoint.py | |
pytest --verbose checkpoint/test_shared_weights.py | |
pytest --verbose launcher/test_ds_arguments.py launcher/test_run.py | |
pytest --verbose moe/test_moe_tp.py | |
pytest --verbose monitor/* | |
pytest --verbose runtime/test_ds_config_model.py | |
pytest --verbose runtime/pipe/test_pipe_schedule.py | |
pytest --verbose runtime/zero/test_zero_config.py | |
pytest --verbose runtime/zero/test_zero_tiled.py | |
pytest --verbose runtime/zero/test_zeropp.py | |
pytest --verbose runtime/test_autocast.py | |
pytest --verbose runtime/test_data.py | |
pytest --verbose runtime/test_runtime_utils.py | |
pytest --verbose runtime/activation_checkpointing/* | |
pytest --verbose runtime/utils/* | |
pytest --verbose runtime/zero/test_zero_dynamic_class.py |