Rework --enable_generic_interface and add tests #24552

adrianlizarraga · 2025-04-25T22:43:07Z

Description

Introduces USE_<EP>_PROVIDER_INTERFACE pre-processor macros that indicate when an EP interface is enabled but the full EP is not being compiled.
- Previously, the CMake configuration turned on USE_<EP> for both use cases. This prevented tests from determining whether the full EP or only the interface was available, which caused test failures. It also turned on all EP code paths in core ORT code at the same time, which caused compilation and logic errors.
Adds the new NV EP to list of EPs whose interface is enabled with ORT is built with --enable_generic_interface
Updates the Windows Arm64 QNN CI Pipeline to actually use the --enable_generic_interface flag.
- Previously, It was not actually being passed to the build command, so no unit tests were being run with the flag enabled.
Adds unit tests to check that adding an EP to the session options fails when only the generic interface (but not the full EP) is built.

CI Pipelines that use --enable_generic_interface

Windows ARM64 QNN CI Pipeline:
- Builds ORT with --use_qnn --enable_generic_interface and runs all normal QNN EP unit tests.
- Builds ORT with --use_qnn --enable_generic_interface and runs new unit tests that try to add the following EPs to the session options (expect failure): OpenVINO, CUDA, NV, TensorRT, VitisAI
Build and Test OpenVINO EP (AlamLinux8, Py3.12) / build_test_pipeline:
- Builds ORT with --use_openvino --enable_generic_interface and runs all normal OpenVINO EP unit tests.
- Builds ORT with --use_openvino --enable_generic_interface and runs new unit tests that try to add the following EPs to the session options (expect failure): QNN, CUDA, NV, TensorRT, VitisAI
windows_x64_release_ep_generic_interface
- Builds ORT with --enable_generic_interface and now runs CPU EP unit tests (didn't previously).

Motivation and Context

Fix use of --enable_generic_interface and make sure tests actually run.

tools/ci_build/github/azure-pipelines/win-qnn-arm64-ci-pipeline.yml

… (but not compiling full EP)

…DA interface option

tools/ci_build/build.py

onnxruntime/python/onnxruntime_pybind_state_common.cc

…but not full EP) is built fails

cmake/CMakeLists.txt

onnxruntime/core/providers/provider_factory_creators.h

onnxruntime/test/shared_lib/test_session_options.cc

tools/ci_build/github/azure-pipelines/win-qnn-arm64-ci-pipeline.yml

cmake/CMakeLists.txt

adrianlizarraga · 2025-04-29T23:16:31Z

Hi @snnn, Could you please take a look at this PR? I believe it addresses your concerns in this other PR: #24368

…rface

- Introduces `USE_<EP>_PROVIDER_INTERFACE` pre-processor macros that indicate when an EP interface is enabled but the full EP is not being compiled. - Previously, the CMake configuration turned on `USE_<EP>` for both use cases. This prevented tests from determining whether the full EP or only the interface was available, which caused test failures. It also turned on all EP code paths in core ORT code at the same time, which caused compilation and logic errors. - Adds the new NV EP to list of EPs whose interface is enabled with ORT is built with `--enable_generic_interface` - Updates the Windows Arm64 QNN CI Pipeline to actually use the `--enable_generic_interface` flag. - Previously, It was not actually being passed to the build command, so no unit tests were being run with the flag enabled. - Adds unit tests to check that adding an EP to the session options fails when only the generic interface (but not the full EP) is built. - Windows ARM64 QNN CI Pipeline: - Builds ORT with `--use_qnn --enable_generic_interface` and runs all normal QNN EP unit tests. - Builds ORT with `--use_qnn --enable_generic_interface` and runs new unit tests that try to add the following EPs to the session options (expect failure): OpenVINO, CUDA, NV, TensorRT, VitisAI - Build and Test OpenVINO EP (AlamLinux8, Py3.12) / build_test_pipeline: - Builds ORT with `--use_openvino --enable_generic_interface` and runs all normal OpenVINO EP unit tests. - Builds ORT with `--use_openvino --enable_generic_interface` and runs new unit tests that try to add the following EPs to the session options (expect failure): QNN, CUDA, NV, TensorRT, VitisAI - windows_x64_release_ep_generic_interface - Builds ORT with `--enable_generic_interface` and now runs CPU EP unit tests (didn't previously). Fix use of `--enable_generic_interface` and make sure tests actually run.

### Description Cherry pick the following into [rel-1.22.0](https://github.com/microsoft/onnxruntime/tree/rel-1.22.0) - (#24491) - (#24509) - (#24564) - (#24574) - (#24582) - (#24584) - (#24568) - (#24587) - (#24563) - (#24592) - (#24526) - (#24552) - (#24588) - (#24605) - (#24606) --------- Co-authored-by: Jing Fang <[email protected]> Co-authored-by: Tianlei Wu <[email protected]> Co-authored-by: Baiju Meswani <[email protected]> Co-authored-by: Scott McKay <[email protected]> Co-authored-by: Mark Schofield <[email protected]> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Edward Chen <[email protected]> Co-authored-by: Ashwath Shankarnarayan <[email protected]> Co-authored-by: saurabh <[email protected]> Co-authored-by: Adrian Lizarraga <[email protected]> Co-authored-by: Hector Li <[email protected]>

### Description - Introduces `USE_<EP>_PROVIDER_INTERFACE` pre-processor macros that indicate when an EP interface is enabled but the full EP is not being compiled. - Previously, the CMake configuration turned on `USE_<EP>` for both use cases. This prevented tests from determining whether the full EP or only the interface was available, which caused test failures. It also turned on all EP code paths in core ORT code at the same time, which caused compilation and logic errors. - Adds the new NV EP to list of EPs whose interface is enabled with ORT is built with `--enable_generic_interface` - Updates the Windows Arm64 QNN CI Pipeline to actually use the `--enable_generic_interface` flag. - Previously, It was not actually being passed to the build command, so no unit tests were being run with the flag enabled. - Adds unit tests to check that adding an EP to the session options fails when only the generic interface (but not the full EP) is built. #### CI Pipelines that use --enable_generic_interface - Windows ARM64 QNN CI Pipeline: - Builds ORT with `--use_qnn --enable_generic_interface` and runs all normal QNN EP unit tests. - Builds ORT with `--use_qnn --enable_generic_interface` and runs new unit tests that try to add the following EPs to the session options (expect failure): OpenVINO, CUDA, NV, TensorRT, VitisAI - Build and Test OpenVINO EP (AlamLinux8, Py3.12) / build_test_pipeline: - Builds ORT with `--use_openvino --enable_generic_interface` and runs all normal OpenVINO EP unit tests. - Builds ORT with `--use_openvino --enable_generic_interface` and runs new unit tests that try to add the following EPs to the session options (expect failure): QNN, CUDA, NV, TensorRT, VitisAI - windows_x64_release_ep_generic_interface - Builds ORT with `--enable_generic_interface` and now runs CPU EP unit tests (didn't previously). ### Motivation and Context Fix use of `--enable_generic_interface` and make sure tests actually run.

snnn · 2025-09-05T20:48:31Z

This PR has been included in the rel-1.22.0 branch. Removing the release:1.22.0 label.

adrianlizarraga added 2 commits April 25, 2025 15:40

Fix use of --use_generic_interface in QNN pipeline

253ef23

Use the correct option name

5f015e0

adrianlizarraga changed the title ~~[QNN EP] Fix use of --use_generic_interface in QNN pipeline~~ [QNN EP] Fix use of --enable_generic_interface in QNN pipeline Apr 25, 2025

Merge branch 'main' into adrianl/fix-qnn-use-of-generic-interface-flag

98fdafe

adrianlizarraga mentioned this pull request Apr 28, 2025

[ort-build] Pass ORT_EXTRA_INTERFACE_FLAGS to onnxruntime_session #24368

Closed

karim-vad reviewed Apr 28, 2025

View reviewed changes

tools/ci_build/github/azure-pipelines/win-qnn-arm64-ci-pipeline.yml Outdated Show resolved Hide resolved

adrianlizarraga added 3 commits April 29, 2025 00:34

Use a separate preprocessor macro for when an EP interface is enabled…

3bc773c

… (but not compiling full EP)

Add provider interface flags to onnxruntime_pybind11_state. Remove CU…

105147f

…DA interface option

Merge branch 'main' into adrianl/fix-qnn-use-of-generic-interface-flag

a668377

karim-vad reviewed Apr 29, 2025

View reviewed changes

tools/ci_build/build.py Show resolved Hide resolved

karim-vad reviewed Apr 29, 2025

View reviewed changes

onnxruntime/python/onnxruntime_pybind_state_common.cc Show resolved Hide resolved

Add unit tests that check that adding an EP when only the interface (…

baf47fa

…but not full EP) is built fails

adrianlizarraga changed the title ~~[QNN EP] Fix use of --enable_generic_interface in QNN pipeline~~ [QNN EP] Rework --enable_generic_interface and add tests Apr 29, 2025