Update deepspeed.yaml #44
Workflow file for this run
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: huawei-ascend-npu | |
| defaults: | |
| run: | |
| shell: bash -ieo pipefail {0} | |
| on: | |
| workflow_dispatch: | |
| pull_request: | |
| paths: | |
| - '.github/workflows/deepspeed.yaml' | |
| - 'requirements/**' | |
| schedule: | |
| - cron: "0 0 * * *" | |
| push: | |
| paths: | |
| - '.github/workflows/deepspeed.yaml' | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| permissions: | |
| contents: read | |
| issues: write | |
| jobs: | |
| unit-tests: | |
| runs-on: [self-hosted, ascend, npu] | |
| container: | |
| image: ascendai/cann | |
| ports: | |
| - 80 | |
| volumes: | |
| - /usr/local/dcmi:/usr/local/dcmi | |
| - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi | |
| - /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ | |
| - /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info | |
| - /etc/ascend_install.info:/etc/ascend_install.info | |
| options: --network host | |
| --name deepspeed_unit-tests | |
| --device /dev/davinci6 | |
| --device /dev/davinci_manager | |
| --device /dev/devmm_svm | |
| --device /dev/hisi_hdc | |
| --shm-size "20g" | |
| --entrypoint /bin/bash | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Install pytorch | |
| run: | | |
| npu-smi info | |
| apt-get update | |
| apt-get install sudo | |
| pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple | |
| source /root/.bashrc | |
| pip install torch==2.2.0 torchvision==0.17.0 torch_npu==2.2.0 torchaudio==2.2.0 numpy==1.26.4 cloudpickle tornado ml-dtypes | |
| python << EOF | |
| if __name__ == '__main__': | |
| import torch | |
| import torch_npu | |
| torch_npu.npu.set_device("npu:0") | |
| print(f"Device Name: {torch.npu.get_device_name(0)}") | |
| print(f"Device Count: {torch.npu.device_count()}") | |
| print(f"Device Available: {torch.npu.is_available()}") | |
| EOF | |
| - name: Install transformers | |
| run: | | |
| source /root/.bashrc | |
| echo "y" | apt-get install git | |
| git clone https://github.com/huggingface/transformers | |
| cd transformers | |
| git rev-parse --short HEAD | |
| pip install . | |
| - name: Install deepspeed | |
| run: | | |
| source /root/.bashrc | |
| git clone --depth=1 https://github.com/microsoft/DeepSpeed.git | |
| pip install -r requirements/requirements_deepspeed.txt | |
| cd DeepSpeed | |
| pip install .[1bit,autotuning,inf] | |
| ds_report | |
| - id: setup-venv | |
| uses: ./DeepSpeed/.github/workflows/setup-venv | |
| - name: Python environment | |
| run: | | |
| source /root/.bashrc | |
| pip list | |
| - name: PyTorch Lightning Tests | |
| run: | | |
| unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch | |
| pip install pytorch-lightning | |
| pip install "protobuf<4.21.0" | |
| cd DeepSpeed/tests | |
| pytest $PYTEST_OPTS lightning/ | |
| continue-on-error: true | |
| - name: MII unit tests | |
| run: | | |
| BRANCH="main" | |
| if [[ ! -z "${{ github.event.inputs.mii_branch }}" ]]; then | |
| BRANCH="${{ github.event.inputs.mii_branch }}" | |
| fi | |
| echo "Cloning DeepSpeed-MII branch: $BRANCH" | |
| git clone -b $BRANCH --depth=1 https://github.com/microsoft/DeepSpeed-MII.git | |
| cd DeepSpeed-MII | |
| pip install .[dev] | |
| unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch | |
| cd tests/legacy | |
| pytest $PYTEST_OPTS --forked -m "deepspeed" ./ | |
| continue-on-error: true | |
| - name: HF Accelerate tests | |
| run: | | |
| unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch | |
| git clone https://github.com/huggingface/accelerate | |
| cd accelerate | |
| git rev-parse --short HEAD | |
| # installing dependencies | |
| pip install .[testing] | |
| # force protobuf version due to issues | |
| pip install "protobuf<4.21.0" | |
| # tmp fix: force newer datasets version | |
| #pip install "datasets>=2.0.0" | |
| pip list | |
| pytest $PYTEST_OPTS --color=yes --durations=0 --verbose tests/deepspeed | |
| continue-on-error: true | |
| - name: Unit tests | |
| run: | | |
| source /root/.bashrc | |
| unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch | |
| cd DeepSpeed/tests/unit/ | |
| # pytest --verbose $PYTEST_OPTS --forked -n 4 unit/ | |
| # pytest $PYTEST_OPTS --forked -m 'sequential' 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 model_parallelism/* | |
| pytest --verbose moe/test_moe_tp.py | |
| pytest --verbose monitor/* | |
| pytest --verbose utils/* | |
| 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 | |