Add FA4 RoPE fusion path for low-precision attention #9413
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 1xH100 Tests | |
| on: | |
| push: | |
| branches: | |
| - main | |
| - 'gh/**' | |
| pull_request: | |
| branches: | |
| - main | |
| - 'gh/**' | |
| concurrency: | |
| group: 1xH100_tests-${{ github.workflow }}-${{ 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: H100 | |
| runs-on: linux.aws.h100 | |
| torch-spec: '--pre torch torchvision torchaudio mslk --index-url https://download.pytorch.org/whl/nightly/cu126' | |
| gpu-arch-type: "cuda" | |
| gpu-arch-version: "12.6" | |
| permissions: | |
| id-token: write | |
| contents: read | |
| uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main | |
| with: | |
| timeout: 90 | |
| runner: ${{ matrix.runs-on }} | |
| gpu-arch-type: ${{ matrix.gpu-arch-type }} | |
| gpu-arch-version: ${{ matrix.gpu-arch-version }} | |
| submodules: recursive | |
| script: | | |
| conda create -n venv python=3.10 -y | |
| conda activate venv | |
| export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH | |
| python -m pip install --upgrade pip | |
| pip install uv | |
| pip install ${{ matrix.torch-spec }} | |
| pip install -U --pre flashinfer-python --index-url https://flashinfer.ai/whl/nightly/ --no-deps | |
| pip install apache-tvm-ffi | |
| pip install nvidia-ml-py | |
| uv pip install -r dev-requirements.txt | |
| pip install . --no-build-isolation -vv | |
| pytest test/integration --verbose -s | |
| pytest test/dtypes/test_affine_quantized_float.py --verbose -s | |
| pytest test/quantization/quantize_/workflows/float8 --verbose -s | |
| python test/quantization/quantize_/workflows/int4/test_int4_tensor.py | |
| python test/quantization/quantize_/workflows/int4/test_int4_preshuffled_tensor.py | |
| ./test/float8/test_everything_single_gpu.sh | |
| pytest test/prototype/mx_formats/ --verbose -s | |
| pytest test/prototype/moe_training/test_fp8_grouped_mm.py --verbose -s | |
| pytest test/prototype/moe_training/test_mxfp8_grouped_mm.py --verbose -s | |
| pytest test/prototype/moe_training/test_training.py --verbose -s |