pythonapp-hyena-gpu.yml

# Optional self-hosted GPU CI for the HyenaND test surface.
#
# This workflow exercises the CUDA-required Hyena tests
# (tests/networks/blocks/test_hyena_block.py CUDA cases, the four-paper-variant
# forward and gradient cases in tests/networks/nets/test_swin_unetr.py and
# tests/networks/nets/test_hyena_nd_unetr.py, the SwinUNETR(use_hyena=False)
# golden-hash backward-compat regression, and sliding-window inference).
#
# Disabled by default (``if: false``).  To enable:
#   1. Ensure a self-hosted runner with the labels below is available, AND
#   2. Ensure the runner has CUDA-capable hardware visible (the existing
#      ``pythonapp-gpu.yml`` uses ``--gpus all`` against ``[self-hosted, linux,
#      x64, common]``).  Reuse that pool if possible.
#   3. Flip ``if: false`` to ``if: github.event.pull_request.merged != true``
#      (mirroring ``pythonapp-gpu.yml``'s gating pattern).
#
# nvsubquadratic (Hyena's optional dep) requires Python >= 3.10; any NGC base with
# Python >= 3.10 works. The accelerated [cuda] kernels build against the container nvcc.

name: hyena-gpu

on:
  workflow_dispatch:

concurrency:
  group: hyena-gpu-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

jobs:
  GPU-Hyena:
    if: ${{ false }}  # See header for enable instructions.
    strategy:
      matrix:
        environment:
          # NGC PyTorch 25.05 ships Python 3.12 and CUDA 12.5.  Bump as needed.
          - "NGC25.05+PY312"
        include:
          - environment: NGC25.05+PY312
            base: "nvcr.io/nvidia/pytorch:25.05-py3"
    container:
      image: ${{ matrix.base }}
      options: --gpus all --env NVIDIA_DISABLE_REQUIRE=true
    runs-on: [self-hosted, linux, x64, common]
    steps:
    - uses: actions/checkout@v6
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip wheel
        python -c "import sys; assert sys.version_info >= (3, 10), f'Python >= 3.10 required for nvsubquadratic, got {sys.version}'"
        python -m pip install -r requirements-dev.txt
        python -m pip install -e .
        # Install nvsubquadratic with --no-deps: the default torch_fft path needs only
        # torch + einops + omegaconf, and nvsubquadratic pins torch>=2.10,<2.11 which can
        # clash with the container's torch.  To exercise the accelerated fused CUDA
        # kernels instead, install the [cuda] extra (subquadratic-ops-torch-cu12, builds
        # against the container's nvcc) and set fft_backend="subq_ops" in the tests.
        python -m pip install omegaconf
        python -m pip install --no-deps 'nvsubquadratic>=0.1.1'
        python -m pip list
      shell: bash
    - name: Verify CUDA + nvsubquadratic
      run: |
        nvidia-smi
        python -c "import torch; assert torch.cuda.is_available(); print('CUDA OK:', torch.cuda.get_device_name(0))"
        python -c "from monai.networks.blocks.hyena import is_nvsubquadratic_available; \
                   assert is_nvsubquadratic_available(), 'nvsubquadratic must be importable'"
      shell: bash
    - name: Run Hyena test suite (CUDA + no-CUDA)
      run: |
        python -m pytest -v \
          tests/networks/blocks/test_hyena_block.py \
          tests/networks/nets/test_hyena_nd_unetr.py \
          tests/networks/nets/test_swin_unetr.py
      shell: bash