xpu-compile #15
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-compile | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| - cron: "0 0 * * *" | |
| pull_request: | |
| paths: | |
| - ".github/workflows/xpu-compile.yml" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| permissions: | |
| contents: read | |
| issues: write | |
| jobs: | |
| compile-tests: | |
| runs-on: [self-hosted, intel, xpu] | |
| container: | |
| image: intel/oneapi-basekit:2024.2.1-0-devel-ubuntu22.04 | |
| 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: Install prerequisite | |
| run: | | |
| apt-get update | |
| apt-get install clinfo libaio-dev python3-pip -y | |
| pip install torch==2.3.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/us/torch/ | |
| pip install intel-extension-for-pytorch==2.3.110+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/us/intel-extension-for-pytorch/ | |
| pip install oneccl_bind_pt==2.3.100+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/us/oneccl-bind-pt/ | |
| pip install torchvision==0.18.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/us/torchvision/ | |
| pip install https://github.com/intel/intel-xpu-backend-for-triton/releases/download/v3.0.0b2/triton_xpu-3.0.0b2-cp310-cp310-linux_x86_64.whl | |
| pip install py-cpuinfo numpy | |
| pip install .[dev,autotuning] | |
| - name: Check container state | |
| run: | | |
| ldd --version | |
| ds_report | |
| python3 -c "import torch; print('torch:', torch.__version__, torch)" | |
| python3 -c "import torch; import intel_extension_for_pytorch; print('XPU available:', torch.xpu.is_available())" | |
| python3 -c "from deepspeed.accelerator import get_accelerator; print('accelerator:', get_accelerator()._name)" | |
| pip list | |
| - name: Compile Status | |
| shell: bash | |
| run: | | |
| echo "# torch.compile graph breaks" >> $GITHUB_STEP_SUMMARY | |
| export FI_HMEM=system | |
| ulimit -n 1048575 | |
| cd tests/torch_compile | |
| export ZE_AFFINITY_MASK=0,1 | |
| echo "## ZeRO stage 3" >> $GITHUB_STEP_SUMMARY | |
| deepspeed test_compile.py --deepspeed_config ds_config_z3.json 2>&1 | tee log_z3.txt | |
| # for each line start with 'dynamo_output', extract the second field and following fields and append to GITHUB_STEP_SUMMARY using awk | |
| cat log_z3.txt | awk '/^dynamo_output/ {$1=""; print $0}' >> $GITHUB_STEP_SUMMARY | |
| echo "## ZeRO stage 2" >> $GITHUB_STEP_SUMMARY | |
| deepspeed test_compile.py --deepspeed_config ds_config_z2.json 2>&1 | tee log_z2.txt | |
| cat log_z2.txt | awk '/^dynamo_output/ {$1=""; print $0}' >> $GITHUB_STEP_SUMMARY |