Add Float8 Weight Only and FP8 weight + dynamic activation #3090
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: Run Regression Tests | |
| on: | |
| push: | |
| branches: | |
| - main | |
| pull_request: | |
| branches: | |
| - main | |
| 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: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| include: | |
| - name: CUDA 2.2.2 | |
| runs-on: linux.g5.12xlarge.nvidia.gpu | |
| torch-spec: 'torch==2.2.2 "numpy<2" ' | |
| gpu-arch-type: "cuda" | |
| gpu-arch-version: "12.1" | |
| - name: CUDA 2.3 | |
| runs-on: linux.g5.12xlarge.nvidia.gpu | |
| torch-spec: 'torch==2.3.0' | |
| gpu-arch-type: "cuda" | |
| gpu-arch-version: "12.1" | |
| - name: CUDA 2.4 | |
| runs-on: linux.g5.12xlarge.nvidia.gpu | |
| torch-spec: 'torch==2.4.0' | |
| gpu-arch-type: "cuda" | |
| gpu-arch-version: "12.1" | |
| - name: CUDA Nightly | |
| runs-on: linux.g5.12xlarge.nvidia.gpu | |
| torch-spec: '--pre torch --index-url https://download.pytorch.org/whl/nightly/cu121' | |
| gpu-arch-type: "cuda" | |
| gpu-arch-version: "12.1" | |
| - name: CPU 2.2.2 | |
| runs-on: linux.4xlarge | |
| torch-spec: 'torch==2.2.2 --index-url https://download.pytorch.org/whl/cpu "numpy<2" ' | |
| gpu-arch-type: "cpu" | |
| gpu-arch-version: "" | |
| - name: CPU 2.3 | |
| runs-on: linux.4xlarge | |
| torch-spec: 'torch==2.3.0 --index-url https://download.pytorch.org/whl/cpu' | |
| gpu-arch-type: "cpu" | |
| gpu-arch-version: "" | |
| - name: CPU 2.4 | |
| runs-on: linux.4xlarge | |
| torch-spec: 'torch==2.4.0 --index-url https://download.pytorch.org/whl/cpu' | |
| gpu-arch-type: "cpu" | |
| gpu-arch-version: "" | |
| - name: CPU Nightly | |
| runs-on: linux.4xlarge | |
| torch-spec: '--pre torch --index-url https://download.pytorch.org/whl/nightly/cpu' | |
| gpu-arch-type: "cpu" | |
| gpu-arch-version: "" | |
| uses: pytorch/test-infra/.github/workflows/linux_job.yml@main | |
| with: | |
| timeout: 60 | |
| runner: ${{ matrix.runs-on }} | |
| gpu-arch-type: ${{ matrix.gpu-arch-type }} | |
| gpu-arch-version: ${{ matrix.gpu-arch-version }} | |
| script: | | |
| conda create -n venv python=3.9 -y | |
| conda activate venv | |
| echo "::group::Install newer objcopy that supports --set-section-alignment" | |
| yum install -y devtoolset-10-binutils | |
| export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH | |
| python -m pip install --upgrade pip | |
| pip install ${{ matrix.torch-spec }} | |
| pip install -r dev-requirements.txt | |
| pip install . | |
| pytest test --verbose -s |