tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

don't run multigpu tests twice, run SP in separate test (#2542)

Browse Source 
* don't run multigpu tests twice, run SP in separate test

* fix multiline
This commit is contained in:
Wing Lian
2025-04-21 10:24:13 -04:00
committed by GitHub
parent 4ce469d32e
commit b640db1dbc
3 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
cicd/multigpu.sh
View File

@@ -1,13 +1,10 @@
#!/bin/bash #!/bin/bash
set -e 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) # Only run two tests at a time to avoid OOM on GPU (with coverage collection)
pytest -v -n2 \ 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/ \ /workspace/axolotl/tests/e2e/multigpu/ \
--cov=axolotl \ --cov=axolotl \
--cov-report=xml:multigpu-coverage.xml --cov-report=xml:multigpu-coverage.xml
@@ -17,6 +14,11 @@ pytest -v --durations=10 -n1 /workspace/axolotl/tests/e2e/multigpu/solo/ \
--cov-append \ --cov-append \
--cov-report=xml:multigpu-coverage.xml --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 # Upload coverage to Codecov
if [ -f multigpu-coverage.xml ]; then if [ -f multigpu-coverage.xml ]; then
codecov -f multigpu-coverage.xml -F multigpu,docker-tests,pytorch-${PYTORCH_VERSION} codecov -f multigpu-coverage.xml -F multigpu,docker-tests,pytorch-${PYTORCH_VERSION}

0
tests/e2e/multigpu/patched/__init__.py Normal file
View File

2
tests/e2e/multigpu/test_sp.py → tests/e2e/multigpu/patched/test_sp.py
View File

@@ -10,7 +10,7 @@ from transformers.testing_utils import get_torch_dist_unique_port
from axolotl.utils.dict import DictDefault from axolotl.utils.dict import DictDefault
from ..utils import check_tensorboard from ...utils import check_tensorboard
os.environ["WANDB_DISABLED"] = "true" os.environ["WANDB_DISABLED"] = "true"