[mxfp8 training] update triton_to_mxfp8_dim0 nan handling; fix offset… #1675
This file contains hidden or 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: Run Regression Tests on ROCm | |
| on: | |
| push: | |
| branches: | |
| - main | |
| tags: | |
| - ciflow/rocm/* | |
| concurrency: | |
| group: regression_test-${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_number || github.ref }} | |
| cancel-in-progress: true | |
| env: | |
| HF_TOKEN: ${{ secrets.HF_TOKEN }} | |
| jobs: | |
| test-nightly: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| include: | |
| - name: ROCM Nightly | |
| runs-on: linux.rocm.gpu.gfx942.1 | |
| torch-spec: '--pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/rocm7.0' | |
| gpu-arch-type: "rocm" | |
| gpu-arch-version: "7.0" | |
| docker-image: pytorch/manylinux2_28-builder:rocm7.0 | |
| permissions: | |
| id-token: write | |
| contents: read | |
| uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main | |
| with: | |
| timeout: 210 | |
| no-sudo: ${{ matrix.gpu-arch-type == 'rocm' }} | |
| runner: ${{ matrix.runs-on }} | |
| gpu-arch-type: ${{ matrix.gpu-arch-type }} | |
| gpu-arch-version: ${{ matrix.gpu-arch-version }} | |
| docker-image: ${{ matrix.docker-image }} | |
| submodules: recursive | |
| script: | | |
| conda create -n venv python=3.10 -y | |
| conda activate venv | |
| python -m pip install --upgrade pip | |
| pip install ${{ matrix.torch-spec }} | |
| pip install -r dev-requirements.txt | |
| pip install . --no-build-isolation | |
| export CONDA=$(dirname $(dirname $(which conda))) | |
| export LD_LIBRARY_PATH=$CONDA/lib/:$LD_LIBRARY_PATH | |
| pytest test --verbose -s |