Run GPU Tests on Rapids Nightly at midnight UTC (#463)

.github/workflows/gpuci.yml

@@ -1,6 +1,8 @@
 name: "GPU CI/CD"
 
 on:
+  schedule:
+    - cron: '0 0 * * *'  # scheduled trigger for nightly builds, runs at midnight UTC every day
   push:
     branches:
       - main
@@ -21,34 +23,41 @@ concurrency:
 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' }}
+    # "build-container" job is run if the "gpuci" label is added to the PR / merge to main / scheduled run
+    if: ${{ github.event.label.name == 'gpuci' || github.ref == 'refs/heads/main' || github.event_name == 'schedule' }}
     uses: NVIDIA/NeMo-FW-CI-templates/.github/workflows/[email protected]
     with:
       image-name: nemo_curator_container
       dockerfile: Dockerfile
-      image-label: nemo-curator
+      # Use different image-label / build-args based on event type
+      # Given we only use "schedule" event for nightly builds, we use that in our conditions to distinguish nightly vs stable
+      image-label: ${{ github.event_name == 'schedule' && 'nemo-curator-nightly' || 'nemo-curator' }}
       build-args: |
-        IMAGE_LABEL=nemo-curator
+        IMAGE_LABEL=${{ github.event_name == 'schedule' && 'nemo-curator-nightly' || 'nemo-curator' }}
         REPO_URL=https://github.com/${{ github.repository }}.git
         CURATOR_COMMIT=${{ github.sha }}
+        BUILD_TYPE=${{ github.event_name == 'schedule' && 'nightly' || 'stable' }}
       prune-filter-timerange: 24h
+      # We don't want to use cache for Nighlty Runs, as we want to build a fresh image each time
+      use_cache: ${{ github.event_name != 'schedule' }}
 
   # 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' }}
+    # "run-gpu-tests" job is run if the "gpuci" label is added to the PR / merged to main / scheduled run
+    if: ${{ github.event.label.name == 'gpuci' || github.ref == 'refs/heads/main' || github.event_name == 'schedule' }}
+    env:
+      CONTAINER_NAME: ${{ github.event_name == 'schedule' && 'nemo-curator-nightly-container' || 'nemo-curator-container' }}
 
     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 [ "$(docker ps -aq -f name=nemo-curator-container)" ]; then
-            docker rm -f nemo-curator-container
+        if [ "$(docker ps -aq -f name=$CONTAINER_NAME)" ]; then
+            docker rm -f $CONTAINER_NAME
         fi
 
       # This runs the container which was pushed by build-container, which we call "nemo-curator-container"
@@ -57,33 +66,33 @@ jobs:
       # `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"
+        docker run --gpus all --name $CONTAINER_NAME -d nemoci.azurecr.io/nemo_curator_container:${{ 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
+        docker exec $CONTAINER_NAME 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
+        docker exec $CONTAINER_NAME 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
+        docker exec $CONTAINER_NAME 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
+        docker stop $CONTAINER_NAME && docker rm $CONTAINER_NAME

Dockerfile

@@ -6,6 +6,7 @@ ARG PYTHON_VER=3.10
 ARG IMAGE_LABEL
 ARG REPO_URL
 ARG CURATOR_COMMIT
+ARG BUILD_TYPE=stable
 
 FROM rapidsai/ci-conda:cuda${CUDA_VER}-${LINUX_VER}-py${PYTHON_VER} as curator-update
 # Needed to navigate to and pull the forked repository's changes
@@ -30,6 +31,7 @@ WORKDIR /opt
 
 # Re-declare ARGs after new FROM to make them available in this stage
 ARG CUDA_VER
+ARG BUILD_TYPE
 
 # Install the minimal libcu* libraries needed by NeMo Curator
 RUN conda create -y --name curator -c nvidia/label/cuda-${CUDA_VER} -c conda-forge \
@@ -50,15 +52,23 @@ RUN \
 --mount=type=bind,source=/opt/NeMo-Curator/pyproject.toml,target=/opt/NeMo-Curator/pyproject.toml,from=curator-update \
   cd /opt/NeMo-Curator && \
   source activate curator && \
-  pip install ".[all]"
+  if [ "$BUILD_TYPE" = "nightly" ]; then \
+    pip install ".[all_nightly]"; \
+  else \
+    pip install ".[all]"; \
+  fi
 
 COPY --from=curator-update /opt/NeMo-Curator/ /opt/NeMo-Curator/
 
 # Clone the user's repository, find the relevant commit, and install everything we need
 RUN bash -exu <<EOF
   source activate curator
   cd /opt/NeMo-Curator/
-  pip install --extra-index-url https://pypi.nvidia.com ".[all]"
+  if [ "$BUILD_TYPE" = "nightly" ]; then \
+    pip install --extra-index-url=https://pypi.anaconda.org/rapidsai-wheels-nightly/simple ".[all_nightly]"; \
+  else \
+    pip install --extra-index-url https://pypi.nvidia.com ".[all]"; \
+  fi
 EOF
 
 ENV PATH /opt/conda/envs/curator/bin:$PATH