diff --git a/cicd/multigpu.sh b/cicd/multigpu.sh index 898cf1155..519ac0133 100755 --- a/cicd/multigpu.sh +++ b/cicd/multigpu.sh @@ -1,13 +1,10 @@ #!/bin/bash set -e -# only run one test at a time so as not to OOM the GPU -pytest -v --durations=10 -n2 /workspace/axolotl/tests/e2e/multigpu/ --ignore=/workspace/axolotl/tests/e2e/multigpu/solo/ -pytest -v --durations=10 -n1 /workspace/axolotl/tests/e2e/multigpu/solo/ - # Only run two tests at a time to avoid OOM on GPU (with coverage collection) pytest -v -n2 \ - --ignore=/workspace/axolotl/tests/e2e/multigpu/solo/ + --ignore=/workspace/axolotl/tests/e2e/multigpu/solo/ \ + --ignore=/workspace/axolotl/tests/e2e/multigpu/patched/ \ /workspace/axolotl/tests/e2e/multigpu/ \ --cov=axolotl \ --cov-report=xml:multigpu-coverage.xml @@ -17,6 +14,11 @@ pytest -v --durations=10 -n1 /workspace/axolotl/tests/e2e/multigpu/solo/ \ --cov-append \ --cov-report=xml:multigpu-coverage.xml +pytest -v --durations=10 -n1 /workspace/axolotl/tests/e2e/multigpu/patched/ \ + --cov=axolotl \ + --cov-append \ + --cov-report=xml:multigpu-coverage.xml + # Upload coverage to Codecov if [ -f multigpu-coverage.xml ]; then codecov -f multigpu-coverage.xml -F multigpu,docker-tests,pytorch-${PYTORCH_VERSION} diff --git a/tests/e2e/multigpu/patched/__init__.py b/tests/e2e/multigpu/patched/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/tests/e2e/multigpu/test_sp.py b/tests/e2e/multigpu/patched/test_sp.py similarity index 99% rename from tests/e2e/multigpu/test_sp.py rename to tests/e2e/multigpu/patched/test_sp.py index 72e5cb88c..1667408f4 100644 --- a/tests/e2e/multigpu/test_sp.py +++ b/tests/e2e/multigpu/patched/test_sp.py @@ -10,7 +10,7 @@ from transformers.testing_utils import get_torch_dist_unique_port from axolotl.utils.dict import DictDefault -from ..utils import check_tensorboard +from ...utils import check_tensorboard os.environ["WANDB_DISABLED"] = "true"