You need a GPU runner to run stuff

Author: joecummings

.github/workflows/docs.yml

@@ -26,25 +26,11 @@ jobs:
           activate-environment: test
           python-version: '3.10'
           auto-activate: false
-      - name: Verify conda environment
-        shell: bash -l {0}
-        run: |
-          conda info
-          which python
-          which conda
       - name: Update pip
         shell: bash -l {0}
         run: python -m pip install --upgrade pip
-      # - name: Install pytorch
-      #   shell: bash -l {0}
-      #   run: pip3 install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu130 --force-reinstall
-      # - name: Install monarch
-      #   shell: bash -l {0}
-      #   run: pip install assets/ci/monarch_no_torch-0.1.0.dev20251010-py3-none-any.whl
       - name: Install torchforge
         shell: bash -l {0}
-        env:
-          GH_TOKEN: ${{ github.token }}
         run: ./scripts/install.sh
       - name: Install docs dependencies
         shell: bash -l {0}
@@ -53,21 +39,6 @@ jobs:
         shell: bash -l {0}
         working-directory: docs
         run: |
-          # Set up library paths to ensure all dependencies are available
-          # This is critical for monarch and other native dependencies that need libpython3.10.so.1.0
-          export LD_LIBRARY_PATH="${CONDA_PREFIX}/lib:${LD_LIBRARY_PATH:-}"
-
-          # Also set CUDA paths if needed
-          if [ -d "/usr/local/cuda-12.9" ]; then
-            export LD_LIBRARY_PATH="/usr/local/cuda-12.9/compat:${LD_LIBRARY_PATH}"
-            export CUDA_HOME=/usr/local/cuda-12.9
-          fi
-
-          # Verify dependencies can be imported before building docs
-          echo "Verifying dependencies..."
-          python -c "import forge; print('✓ torchforge imported successfully')"
-          python -c "import monarch; print('✓ monarch imported successfully')"
-
           # Build docs with -W (warnings as errors) and --keep-going to see all issues
           # Capture exit code but continue to see all errors
           set +e

.github/workflows/gpu_test.yaml

@@ -1,9 +1,6 @@
-name: GPU Tests
+name: Unit Tests (GPU)
 
 on:
-  schedule:
-    # Runs at midnight every day
-    - cron:  '0 0 * * *'
   push:
     branches: [ main ]
   pull_request:
@@ -27,7 +24,7 @@ jobs:
     runs-on: linux.g5.12xlarge.nvidia.gpu
     strategy:
       matrix:
-        python-version: ['3.11']
+        python-version: ['3.10', '3.11', '3.12']
     steps:
       - name: Check out repo
         uses: actions/checkout@v4
@@ -44,9 +41,6 @@ jobs:
         run: ./scripts/install.sh
       - name: Run unit tests with coverage
         # TODO add all tests
-        run: |
-          export LD_PRELOAD=$CONDA/envs/test/lib/libpython3.10.so.1.0
-          export LD_LIBRARY_PATH=$CONDA/envs/test/lib/libpython3.10.so.1.0
-          pytest tests/unit_tests --cov=. --cov-report=xml --durations=20 -vv
+        run: pytest tests/unit_tests --cov=. --cov-report=xml --durations=20 -vv
       - name: Upload Coverage to Codecov
         uses: codecov/codecov-action@v3

.github/workflows/unit_test.yaml

@@ -1,35 +1,44 @@
-name: Unit Tests
+# name: Unit Tests
 
-on:
-  pull_request:
-  push:
-    branches: [ main ]
-  workflow_dispatch:
+# on:
+#   pull_request:
+#   push:
+#     branches: [ main ]
+#   workflow_dispatch:
 
-jobs:
-  unit_tests:
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    strategy:
-      matrix:
-        python-version: ['3.10']
-    steps:
-      - name: Check out repo
-        uses: actions/checkout@v4
-      - name: Setup conda env
-        uses: conda-incubator/setup-miniconda@v2
-        with:
-          auto-update-conda: true
-          miniconda-version: "latest"
-          activate-environment: test
-          python-version: ${{ matrix.python-version }}
-          auto-activate: false
-      # - name: Update pip
-      #   run: python -m pip install --upgrade pip
-      - name: Install torchforge
-        run: ./scripts/install.sh
-      - name: Run unit tests with coverage
-        # TODO add all tests
-        run: pytest tests/unit_tests --cov=. --cov-report=xml --durations=20 -vv
-      - name: Upload Coverage to Codecov
-        uses: codecov/codecov-action@v3
+# jobs:
+#   unit_tests:
+#     runs-on: ubuntu-latest
+#     timeout-minutes: 15
+#     strategy:
+#       matrix:
+#         python-version: ['3.10']
+#     steps:
+#       - name: Check out repo
+#         uses: actions/checkout@v4
+#         with:
+#           fetch-depth: 0
+#       - name: Setup conda env
+#         uses: conda-incubator/setup-miniconda@v2
+#         with:
+#           auto-update-conda: true
+#           miniconda-version: "latest"
+#           activate-environment: test
+#           python-version: '3.10'
+#           auto-activate: false
+#       - name: Verify conda environment
+#         shell: bash -l {0}
+#         run: |
+#           conda info
+#           which python
+#           which conda
+#       - name: Update pip
+#         shell: bash -l {0}
+#         run: python -m pip install --upgrade pip
+#       - name: Install torchforge
+#         run: ./scripts/install.sh
+#       - name: Run unit tests with coverage
+#         # TODO add all tests
+#         run: pytest tests/unit_tests --cov=. --cov-report=xml --durations=20 -vv
+#       - name: Upload Coverage to Codecov
+#         uses: codecov/codecov-action@v3