Add scoped event-time director models #249
There are no files selected for viewing
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,195 @@ | ||
| name: ZMQML Hybrid | ||
|
|
||
| on: | ||
| pull_request: | ||
| branches: | ||
| - master | ||
| push: | ||
| branches: | ||
| - master | ||
|
|
||
| env: | ||
| ROSS_REF: 9b6ccb18f9b9db438bf41b5b221d0ef16a4dac48 | ||
| ZMQML_IMAGE: ghcr.io/codes-org/codes-ci-full:latest | ||
|
|
||
| jobs: | ||
| zmqml-hybrid: | ||
| name: zmqml hybrid workflows | ||
| runs-on: ubuntu-24.04 | ||
|
|
||
| steps: | ||
| - name: Checkout CODES | ||
| uses: actions/checkout@v4 | ||
| with: | ||
| path: codes | ||
|
|
||
| - name: Checkout ROSS | ||
| uses: actions/checkout@v4 | ||
| with: | ||
| repository: ROSS-org/ROSS | ||
| ref: ${{ env.ROSS_REF }} | ||
| path: ross | ||
|
|
||
| - name: Pull full dependency image | ||
| run: docker pull "$ZMQML_IMAGE" | ||
|
|
||
| - name: Create Docker network | ||
| run: docker network create codes-zmqml-ci | ||
|
|
||
| - name: Start ZMQML server container | ||
| run: | | ||
| mkdir -p "$PWD/zmqml-artifacts" | ||
|
|
||
| docker run -d \ | ||
| --name zmqml-server \ | ||
| --network codes-zmqml-ci \ | ||
| -v "$PWD/codes:/work/codes" \ | ||
| -v "$PWD/zmqml-artifacts:/work/zmqml-artifacts" \ | ||
| -w /work/codes/src/surrogate/zmqml \ | ||
| -e ZMQML_ITERATION_HISTORY_LEN=2 \ | ||
| -e ZMQML_ITERATION_HORIZON=3 \ | ||
| -e ZMQML_ITERATION_TRAIN_STRIDE=1 \ | ||
| -e ZMQML_EVENT_TIME_MIN_ROWS=4 \ | ||
| -e ZMQML_EVENT_TIME_EPOCHS=2 \ | ||
| -e ZMQML_RECORD_LOG_PATH=/work/zmqml-artifacts/iteration-records.csv \ | ||
| -e ZMQML_EVENT_TIME_RECORD_LOG_PATH=/work/zmqml-artifacts/event-time-records.csv \ | ||
| "$ZMQML_IMAGE" \ | ||
| bash -euxo pipefail -c ' | ||
| apt-get update | ||
| apt-get install -y python3-zmq python3-numpy python3-sklearn python3-pandas python3-pip gettext-base | ||
|
|
||
| python3 -c "import importlib.util, subprocess, sys; sys.exit(0) if importlib.util.find_spec(\"torch\") else subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"--break-system-packages\", \"torch\", \"--index-url\", \"https://download.pytorch.org/whl/cpu\"])" | ||
|
|
||
| exec python3 -u zmqmlserver.py | ||
| ' | ||
|
|
||
| sleep 5 | ||
| docker ps --filter name=zmqml-server | ||
| docker logs zmqml-server | ||
|
|
||
| - name: Build ROSS and CODES with ZMQML | ||
| run: | | ||
| docker run --rm \ | ||
| --name codes-zmqml-build \ | ||
| --network codes-zmqml-ci \ | ||
| -v "$PWD/codes:/work/codes" \ | ||
| -v "$PWD/ross:/work/ross" \ | ||
| -v "$PWD/ross-install:/work/ross-install" \ | ||
| -w /work \ | ||
| "$ZMQML_IMAGE" \ | ||
| bash -euxo pipefail -c ' | ||
| apt-get update | ||
| apt-get install -y python3-zmq python3-numpy python3-sklearn python3-pandas python3-pip gettext-base | ||
| python3 -c "import importlib.util, subprocess, sys; sys.exit(0) if importlib.util.find_spec(\"torch\") else subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"--break-system-packages\", \"torch\", \"--index-url\", \"https://download.pytorch.org/whl/cpu\"])" | ||
|
|
||
| cmake -S ross -B ross/build -G Ninja \ | ||
| -DCMAKE_BUILD_TYPE=Debug \ | ||
| -DROSS_BUILD_MODELS=ON \ | ||
| -DCMAKE_INSTALL_PREFIX=/work/ross-install | ||
|
|
||
| cmake --build ross/build --target install -j | ||
|
|
||
| cd /work/codes | ||
| rm -rf build | ||
|
|
||
| cmake -S . -B build -G Ninja \ | ||
| -DCMAKE_BUILD_TYPE=Debug \ | ||
| -DBUILD_TESTING=ON \ | ||
| -DCODES_USE_SWM=ON \ | ||
| -DCODES_USE_TORCH=ON \ | ||
| -DCODES_USE_ZEROMQ=ON \ | ||
| -DCODES_ENABLE_ZMQML_HYBRID_TESTS=ON \ | ||
| -DCMAKE_C_COMPILER=mpicc \ | ||
| -DCMAKE_CXX_COMPILER=mpicxx \ | ||
| -DCMAKE_PREFIX_PATH="/work/ross-install;/opt/swm;/opt/argobots" \ | ||
| -DTorch_DIR="$(python3 -c "import torch; print(torch.utils.cmake_prefix_path)")/Torch" | ||
|
|
||
| cmake --build build -j | ||
| ' | ||
|
|
||
| - name: Run ZMQML hybrid tests | ||
| run: | | ||
| docker run --rm \ | ||
| --name codes-zmqml-tests \ | ||
| --network codes-zmqml-ci \ | ||
| -v "$PWD/codes:/work/codes" \ | ||
| -v "$PWD/zmqml-artifacts:/work/zmqml-artifacts" \ | ||
| -w /work/codes \ | ||
| -e ZMQML_ENDPOINT=tcp://zmqml-server:5555 \ | ||
| -e ZMQML_TEST_NP=1 \ | ||
| -e ZMQML_CTL_TIMEOUT=30 \ | ||
| "$ZMQML_IMAGE" \ | ||
| bash -euxo pipefail -c ' | ||
| apt-get update | ||
| apt-get install -y python3-zmq python3-numpy python3-sklearn python3-pandas python3-pip gettext-base | ||
| python3 -c "import importlib.util, subprocess, sys; sys.exit(0) if importlib.util.find_spec(\"torch\") else subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"--break-system-packages\", \"torch\", \"--index-url\", \"https://download.pytorch.org/whl/cpu\"])" | ||
|
|
||
| ctest --test-dir build -N \ | ||
| -R "zmqml-(iteration-time|event-time)-hybrid-workflow.sh" \ | ||
| | tee /tmp/zmqml-ctest-list.txt | ||
|
|
||
| grep -E "Test #[0-9]+: zmqml-(iteration-time|event-time)-hybrid-workflow.sh" \ | ||
| /tmp/zmqml-ctest-list.txt | ||
|
|
||
| ctest --test-dir build \ | ||
| -R "zmqml-(iteration-time|event-time)-hybrid-workflow.sh" \ | ||
| --output-on-failure \ | ||
| --timeout 1200 \ | ||
| -VV | ||
| ' | ||
|
|
||
| - name: Validate ZMQML server logs | ||
| run: | | ||
| mkdir -p "$PWD/zmqml-artifacts" | ||
| docker logs zmqml-server 2>&1 | tee "$PWD/zmqml-artifacts/zmqml-server.log" | ||
|
|
||
| require_log() { | ||
| local pattern="$1" | ||
| local description="$2" | ||
|
|
||
| if ! grep -nE "$pattern" "$PWD/zmqml-artifacts/zmqml-server.log"; then | ||
| echo "::error::Missing server-side ZMQML evidence: $description" | ||
| exit 1 | ||
| fi | ||
| } | ||
|
|
||
| require_log '\[zmqmlserver\] director_debug_prints=1' \ | ||
| 'simulation configured the server debug flag' | ||
|
|
||
| require_log '\[iteration-time records\]' \ | ||
| 'iteration-time records reached the server' | ||
|
|
||
| require_log '\[iteration-time inference\].*predictions=' \ | ||
| 'iteration-time inference reached the server and returned predictions' | ||
|
|
||
| require_log '\[event-time records\]' \ | ||
| 'event-time records reached the server' | ||
|
|
||
| require_log '\[event-time inference\].*predictions=' \ | ||
| 'event-time inference reached the server and returned predictions' | ||
|
|
||
| test -s "$PWD/zmqml-artifacts/iteration-records.csv" | ||
| test -s "$PWD/zmqml-artifacts/event-time-records.csv" | ||
|
|
||
| - name: Dump ZMQML server logs | ||
| if: always() | ||
| run: docker logs zmqml-server || true | ||
|
|
||
| - name: Stop ZMQML server | ||
| if: always() | ||
| run: | | ||
| docker rm -f zmqml-server || true | ||
| docker network rm codes-zmqml-ci || true | ||
|
|
||
| - name: Upload ZMQML logs | ||
| if: always() | ||
| uses: actions/upload-artifact@v4 | ||
| with: | ||
| name: zmqml-hybrid-logs | ||
| path: | | ||
| codes/build/Testing/Temporary/LastTest.log | ||
| codes/build/Testing/Temporary/LastTestsFailed.log | ||
| codes/build/testing-output/** | ||
| zmqml-artifacts/** | ||
| if-no-files-found: ignore | ||
| retention-days: 14 | ||
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
with #255 updating the ci image, this is no longer needed., same for the other places this is done. in the future we should update the docker image with dependencies like this instead of grabbing them in every job. just note that it has to be done in a separate PR because the job that creates the docker image does it on push to master only when the dockerfile changes.