How to update ONNX#

This note is only for ONNX Runtime developers.

If you need to update the ONNX submodule to a different version, follow the steps below.

  1. Update the ONNX submodule

cd cmake/external/onnx
git remote update
git reset --hard <commit_id>
cd ..
git add onnx

(Change the <commit_id> to yours. If you are not sure, use ‘origin/master’. Like ‘git reset –hard origin/master’)

  1. Update cgmanifests/generated/cgmanifest.json. This file should be generated. See cgmanifests/README for instructions.

  2. Update tools/ci_build/github/linux/docker/scripts/requirements.txt and tools/ci_build/github/linux/docker/scripts/manylinux/requirements.txt. Update the commit hash for git+http://github.com/onnx/onnx.git@targetonnxcommithash#egg=onnx.

  3. If there is any change to cmake/external/onnx/onnx/*.in.proto, you need to regenerate OnnxMl.cs. Building onnxruntime with Nuget will do this.

  4. If you are updating ONNX from a released tag to a new commit, please ask Changming (@snnn) to deploy the new test data along with other test models to our CI build machines. This is to ensure that our tests cover every ONNX opset.

  5. Send your PR, and manually queue a build for every packaging pipeline for your branch.

  6. If there is a build failure in stage “Check out of dated documents” in WebAssembly CI pipeline, update ONNX Runtime Web WebGL operator support document:

    • Make sure Node.js is installed (see Prerequisites for instructions).

    • Follow step 1 in js/Build to install dependencies).

    • Follow instructions in Generate document to update document. Commit changes applied to file docs/operators.md.

  7. Usually some newly introduced tests will fail. Then you may need to update

  • onnxruntime/test/onnx/main.cc

  • onnxruntime/test/providers/cpu/model_tests.cc

  • csharp/test/Microsoft.ML.OnnxRuntime.Tests/InferenceTest.cs

  • onnxruntime/test/testdata/onnx_backend_test_series_filters.jsonc

  • onnxruntime/test/testdata/onnx_backend_test_series_overrides.jsonc

  1. If an operator has changed we may need to update optimizers involving that operator.

  • Run find_optimizer_opset_version_updates_required.py, compare with the output from the current main branch, and check for any new warnings.

  • If there are new warnings contact the optimizer owner (which can usually be determined by looking at who edited the file most recently) or failing that ask the ‘ONNX Runtime Shared Core’ mailing list.