Enabling MOE Quantization using linear decomposition #9151
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 Float8 Tests | |
| on: | |
| push: | |
| branches: | |
| - main | |
| - 'gh/**' | |
| pull_request: | |
| branches: | |
| - main | |
| - 'gh/**' | |
| concurrency: | |
| group: float8_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: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| include: | |
| - name: SM-89 | |
| runs-on: linux.g6.4xlarge.experimental.nvidia.gpu | |
| torch-spec: '--pre torch --index-url https://download.pytorch.org/whl/nightly/cu126' | |
| gpu-arch-type: "cuda" | |
| gpu-arch-version: "12.6" | |
| - name: H100 | |
| runs-on: linux.aws.h100 | |
| torch-spec: '--pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu126' | |
| gpu-arch-type: "cuda" | |
| gpu-arch-version: "12.4" | |
| permissions: | |
| id-token: write | |
| contents: read | |
| uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main | |
| with: | |
| timeout: 60 | |
| runner: ${{ matrix.runs-on }} | |
| gpu-arch-type: ${{ matrix.gpu-arch-type }} | |
| gpu-arch-version: ${{ matrix.gpu-arch-version }} | |
| submodules: recursive | |
| script: | | |
| conda create -n venv python=3.9 -y | |
| conda activate venv | |
| export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH | |
| python -m pip install --upgrade pip | |
| pip install ${{ matrix.torch-spec }} | |
| pip install -r dev-requirements.txt | |
| pip install . | |
| pytest test/float8 --verbose -s |