diff --git a/.github/workflows/gpu-ci.yml b/.github/workflows/gpu-ci.yml index 1863939..a35815e 100644 --- a/.github/workflows/gpu-ci.yml +++ b/.github/workflows/gpu-ci.yml @@ -25,6 +25,15 @@ jobs: if: contains(github.event.pull_request.labels.*.name, 'needs-gpu-ci') runs-on: ubuntu-latest timeout-minutes: 60 + + strategy: + fail-fast: false + matrix: + include: + - { gpu_id: "NVIDIA RTX A4000", target_sm: "8.6" } # SM86 + - { gpu_id: "NVIDIA A100 80GB PCIe", target_sm: "8.0" } # SM80 + - { gpu_id: "NVIDIA H100 80GB HBM3", target_sm: "9.0", force_sm90: "1" } # SM90 + steps: - name: Checkout secure orchestrator script from base branch uses: actions/checkout@v4 @@ -67,7 +76,7 @@ jobs: RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }} PR_REPO_URL: ${{ github.event.pull_request.head.repo.clone_url }} PR_SHA: ${{ github.event.pull_request.head.sha }} - # GPU_ID: ${{ matrix.gpu_id }} - # TARGET_SM: ${{ matrix.target_sm }} - # KERNEL_ALIGN_FORCE_SM90: ${{ matrix.force_sm90 }} + GPU_ID: ${{ matrix.gpu_id }} + TARGET_SM: ${{ matrix.target_sm }} + KERNEL_ALIGN_FORCE_SM90: ${{ matrix.force_sm90 }} run: bash ci/run_gpu_ci.sh diff --git a/envs.py b/envs.py index abd12b1..34aded7 100644 --- a/envs.py +++ b/envs.py @@ -12,7 +12,7 @@ def env_flag(name: str, default: bool = False) -> bool: value = os.environ.get(name) - if value is None: + if not value or value.strip() == "": return default normalized = value.strip().lower() if normalized in {"1", "true", "yes", "on"}: