Remove max_text_bytes_per_part
#115
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: "GPU CI/CD" | |
on: | |
push: | |
branches: | |
- main | |
pull_request: | |
branches: | |
# We can run gpuCI on any PR targeting these branches | |
- 'main' | |
- '[rv][0-9].[0-9].[0-9]' | |
- '[rv][0-9].[0-9].[0-9]rc[0-9]' | |
# PR has to be labeled with "gpuCI" label | |
# If new commits are added, the "gpuCI" label has to be removed and re-added to rerun gpuCI | |
types: [ labeled ] | |
concurrency: | |
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | |
cancel-in-progress: true | |
jobs: | |
# First, we build and push a NeMo-Curator container | |
build-container: | |
# "build-container" job is run if the "gpuci" label is added to the PR | |
if: ${{ github.event.label.name == 'gpuci' || github.ref == 'refs/heads/main' }} | |
uses: NVIDIA/NeMo-FW-CI-templates/.github/workflows/[email protected] | |
with: | |
image-name: nemo_curator_container | |
dockerfile: Dockerfile | |
image-label: nemo-curator | |
build-args: | | |
IMAGE_LABEL=nemo-curator | |
REPO_URL=https://github.com/${{ github.repository }}.git | |
CURATOR_COMMIT=${{ github.sha }} | |
prune-filter-timerange: 24h | |
# Then, we run our PyTests in the container we just built | |
run-gpu-tests: | |
needs: build-container | |
# This is the tag on our Azure runner found in Actions -> Runners -> Self-hosted runners | |
# It has 2 A100 GPUs | |
runs-on: self-hosted-azure | |
# "run-gpu-tests" job is run if the "gpuci" label is added to the PR | |
if: ${{ github.event.label.name == 'gpuci' || github.ref == 'refs/heads/main' }} | |
steps: | |
# If something went wrong during the last cleanup, this step ensures any existing container is removed | |
- name: Remove existing container if it exists | |
run: | | |
if [ "$(docker ps -aq -f name=nemo-curator-container)" ]; then | |
docker rm -f nemo-curator-container | |
fi | |
# This runs the container which was pushed by build-container, which we call "nemo-curator-container" | |
# `--gpus all` ensures that all of the GPUs from our self-hosted-azure runner are available in the container | |
# We use "github.run_id" to identify the PR with the commits we want to run the PyTests with | |
# `bash -c "sleep infinity"` keeps the container running indefinitely without exiting | |
- name: Run Docker container | |
run: | | |
docker run --gpus all --name nemo-curator-container -d nemoci.azurecr.io/nemo_curator_container:${{ github.run_id }} bash -c "sleep infinity" | |
# Expect `whoami` to be "azureuser" | |
# Expect `nvidia-smi` to show our 2 A100 GPUs | |
- name: Check GPUs | |
run: | | |
whoami | |
docker exec nemo-curator-container nvidia-smi | |
# In the virtual environment (called "curator") we created in the container, | |
# list all of our packages. Useful for debugging | |
- name: Verify installations | |
run: | | |
docker exec nemo-curator-container pip list | |
# In the virtual environment (called "curator") we created in the container, | |
# run our PyTests marked with `@pytest.mark.gpu` | |
# We specify the `rootdir` to help locate the "pyproject.toml" file (which is in the root directory of the repository), | |
# and then the directory where the PyTests are located | |
- name: Run PyTests with GPU mark | |
run: | | |
docker exec nemo-curator-container pytest -m gpu --rootdir /opt/NeMo-Curator /opt/NeMo-Curator/tests | |
# After running `docker stop`, the container remains in an exited state | |
# It is still present on our system and could be restarted with `docker start` | |
# Thus, we use `docker rm` to permanently removed it from the system | |
- name: Cleanup | |
if: always() | |
run: | | |
docker stop nemo-curator-container && docker rm nemo-curator-container |