Add OpenVINO backend to pip wheel for Linux x86_64 (#18309) by shoumikhin · Pull Request #18309 · pytorch/executorch

shoumikhin · 2026-03-19T06:35:42Z

Summary:

Rewrite the OpenVINO backend runtime to use dlopen/dlsym with the
OpenVINO C API, eliminating the build-time dependency on the OpenVINO
SDK. This follows the QNN backend's proven pattern: the backend links
statically into _portable_lib.so with zero external library dependencies
and loads libopenvino_c.so at runtime via dlopen when the user has the
openvino pip package installed.

Key design decisions:

Use OpenVINO C API (openvino/c/openvino.h) instead of C++ API to
enable dlopen with dlsym function pointers. The C++ class-based API
(ov::Core, ov::InferRequest) cannot be resolved via dlsym.
Forward-declare OpenVINO C types in OpenvinoApi.h instead of
including headers, so there is no build-time SDK dependency at all.
Thread-safe lazy loading via std::call_once in ensure_loaded().
OPENVINO_LIB_PATH env var for explicit library path override.
Backend always registers via static initializer (zero cost); actual
OpenVINO loading deferred to first is_available()/init() call.
No changes to portable_lib.py needed — no RTLD_GLOBAL, no separate
.so, no auditwheel workarounds. The backend is statically linked
into _portable_lib.so like XNNPACK and has no NEEDED entries for
any OpenVINO library.
Enable build on Linux x86_64 unconditionally in setup.py since
there is no build-time dependency.

User experience:
pip install executorch # XNNPACK+QNN+OpenVINO registered
pip install executorch[openvino] # + openvino runtime, backend activates

Differential Revision: D97202714

pytorch-bot · 2026-03-19T06:35:47Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18309

📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 7 New Failures, 5 Cancelled Jobs, 3 Unrelated Failures

As of commit 2e6308c with merge base 60d57e5 ():

NEW FAILURES - The following jobs have failed:

Build Windows Wheels / pytorch/executorch / upload / upload-wheel-py3_10-cpu (gh)
Unable to download artifact(s): Artifact not found for name: pytorch_executorch__3.10_cpu_x64
Build Windows Wheels / pytorch/executorch / upload / upload-wheel-py3_11-cpu (gh)
Unable to download artifact(s): Artifact not found for name: pytorch_executorch__3.11_cpu_x64
Build Windows Wheels / pytorch/executorch / upload / upload-wheel-py3_12-cpu (gh)
Unable to download artifact(s): Artifact not found for name: pytorch_executorch__3.12_cpu_x64
Build Windows Wheels / pytorch/executorch / upload / upload-wheel-py3_13-cpu (gh)
Unable to download artifact(s): Artifact not found for name: pytorch_executorch__3.13_cpu_x64
pull / test-multimodal-linux (gemma3-4b) / linux-job (gh)
RuntimeError: Command docker exec -t 27ce1636d87c5574549a4f87b051ea1cf3b92520ce42d82fce2d8211cc81fb68 /exec failed with exit code 139
trunk / test-arm-backend-vkml (test_pytest_ops_vkml) / linux-job (gh)
RuntimeError: Command docker exec -t 80f8324be411af86f37183878c413289d05f9f706049fa2d3866d4d1f0264a3c /exec failed with exit code 1
trunk / test-coreml-delegate / macos-job (gh)
RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 1

CANCELLED JOBS - The following jobs were cancelled. Please retry:

Build Windows Wheels / pytorch/executorch / build-wheel-py3_10-cpu (gh)
##[error]The operation was canceled.
Build Windows Wheels / pytorch/executorch / build-wheel-py3_11-cpu (gh)
##[error]The operation was canceled.
Build Windows Wheels / pytorch/executorch / build-wheel-py3_12-cpu (gh)
##[error]The operation was canceled.
Build Windows Wheels / pytorch/executorch / build-wheel-py3_13-cpu (gh)
##[error]The operation was canceled.
trunk / test-models-macos-coreml (mv2) / macos-job (gh)

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

pull / unittest / windows / windows-job (gh) (trunk failure)
##[error]The operation was canceled.
pull / unittest-editable / windows / windows-job (gh) (trunk failure)
##[error]The operation was canceled.
trunk / unittest-release / windows / windows-job (gh) (trunk failure)
##[error]The operation was canceled.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

meta-codesync · 2026-03-19T06:35:53Z

@shoumikhin has exported this pull request. If you are a Meta employee, you can view the originating Diff in D97202714.

github-actions · 2026-03-19T06:36:34Z

This PR needs a `release notes:` label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

Copilot

Pull request overview

This PR updates the OpenVINO backend to be included in the Linux x86_64 pip wheel by switching the runtime to dlopen/dlsym against the OpenVINO C API, removing any build-time dependency on the OpenVINO SDK.

Changes:

Reworked the OpenVINO runtime backend to dynamically load libopenvino_c.so and call into the C API via function pointers.
Enabled building and wheel packaging for the OpenVINO backend on Linux x86_64, plus CI wheel checks and an executorch[openvino] optional dependency.
Added/updated documentation describing pip-wheel usage and runtime installation.

Reviewed changes

Copilot reviewed 12 out of 12 changed files in this pull request and generated 7 comments.

Show a summary per file

File	Description
tools/cmake/preset/pybind.cmake	Adds an overridable preset option for `EXECUTORCH_BUILD_OPENVINO`.
setup.py	Turns on OpenVINO backend build for Linux x86_64 and builds the `openvino_backend` target when enabled.
pyproject.toml	Adds an `openvino` optional dependency extra with Linux x86_64 marker.
docs/source/build-run-openvino.md	Adds pip-wheel quick start instructions for Linux x86_64.
backends/openvino/runtime/OpenvinoBackend.h	Switches backend handle/types to C API and adds lazy-loader state.
backends/openvino/runtime/OpenvinoBackend.cpp	Implements runtime `dlopen`/`dlsym` loading and C API execution path.
backends/openvino/runtime/OpenvinoApi.h	Introduces OpenVINO C ABI forward decls + function pointer table.
backends/openvino/README.md	Adds pip-wheel quick start + env var guidance.
backends/openvino/CMakeLists.txt	Removes `find_package(OpenVINO)` and links only `executorch_core` + dl libs.
README-wheel.md	Documents that Linux x86_64 wheels include QNN + OpenVINO (runtime required).
.ci/scripts/wheel/test_linux.py	Asserts `OpenvinoBackend` is registered on Linux x86_64 wheels.
.ci/scripts/wheel/pre_build_script.sh	Installs OpenVINO runtime in Linux x86_64 wheel test environment.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

backends/openvino/runtime/OpenvinoBackend.cpp

backends/openvino/runtime/OpenvinoApi.h

backends/openvino/CMakeLists.txt

docs/source/build-run-openvino.md

backends/openvino/README.md

Summary: Rewrite the OpenVINO backend runtime to use dlopen/dlsym with the OpenVINO C API, eliminating the build-time dependency on the OpenVINO SDK. This follows the QNN backend's proven pattern: the backend links statically into _portable_lib.so with zero external library dependencies and loads libopenvino_c.so at runtime via dlopen when the user has the openvino pip package installed. Key design decisions: - Use OpenVINO C API (openvino/c/openvino.h) instead of C++ API to enable dlopen with dlsym function pointers. The C++ class-based API (ov::Core, ov::InferRequest) cannot be resolved via dlsym. - Forward-declare OpenVINO C types in OpenvinoApi.h instead of including headers, so there is no build-time SDK dependency at all. - Thread-safe lazy loading via std::call_once in ensure_loaded(). - OPENVINO_LIB_PATH env var for explicit library path override. - Backend always registers via static initializer (zero cost); actual OpenVINO loading deferred to first is_available()/init() call. - No changes to portable_lib.py needed — no RTLD_GLOBAL, no separate .so, no auditwheel workarounds. The backend is statically linked into _portable_lib.so like XNNPACK and has no NEEDED entries for any OpenVINO library. - Enable build on Linux x86_64 unconditionally in setup.py since there is no build-time dependency. User experience: pip install executorch # XNNPACK+QNN+OpenVINO registered pip install executorch[openvino] # + openvino runtime, backend activates Differential Revision: D97202714

Copilot

Pull request overview

Refactors the OpenVINO runtime backend to load the OpenVINO C API dynamically at runtime (dlopen/dlsym), enabling inclusion of the OpenVINO backend in the Linux x86_64 pip wheel without a build-time OpenVINO SDK dependency.

Changes:

Reworked OpenVINO runtime to use OpenVINO C API function pointers with thread-safe lazy loading.
Updated build/packaging to enable building the OpenVINO backend into the Linux x86_64 wheel and added an executorch[openvino] optional dependency.
Updated docs and CI wheel checks to reflect/verify OpenVINO backend presence and runtime installation.

Reviewed changes

Copilot reviewed 12 out of 12 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
tools/cmake/preset/pybind.cmake	Adds an overridable preset option for building OpenVINO in pybind builds.
setup.py	Enables OpenVINO build for Linux x86_64 wheels and adds the build target when enabled.
pyproject.toml	Adds `executorch[openvino]` optional dependency with Linux x86_64 marker.
docs/source/build-run-openvino.md	Adds pip-wheel Quick Start instructions for Linux x86_64.
backends/openvino/runtime/OpenvinoBackend.h	Updates backend interface to use C API types and lazy-loading state.
backends/openvino/runtime/OpenvinoBackend.cpp	Implements dlopen/dlsym loading and rewrites init/execute to use the C API.
backends/openvino/runtime/OpenvinoApi.h	Introduces forward declarations + function pointer table for the OpenVINO C API.
backends/openvino/README.md	Documents pip-wheel usage and runtime library path configuration.
backends/openvino/CMakeLists.txt	Removes build-time OpenVINO SDK dependency; links against libdl instead.
README-wheel.md	Documents inclusion of QNN/OpenVINO backends in Linux x86_64 wheels.
.ci/scripts/wheel/test_linux.py	Verifies `OpenvinoBackend` is registered in Linux x86_64 wheel tests.
.ci/scripts/wheel/pre_build_script.sh	Installs OpenVINO runtime package on Linux x86_64 for wheel testing.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

pyproject.toml

docs/source/build-run-openvino.md

Summary: Rewrite the OpenVINO backend runtime to use dlopen/dlsym with the OpenVINO C API, eliminating the build-time dependency on the OpenVINO SDK. This follows the QNN backend's proven pattern: the backend links statically into _portable_lib.so with zero external library dependencies and loads libopenvino_c.so at runtime via dlopen when the user has the openvino pip package installed. Key design decisions: - Use OpenVINO C API (openvino/c/openvino.h) instead of C++ API to enable dlopen with dlsym function pointers. The C++ class-based API (ov::Core, ov::InferRequest) cannot be resolved via dlsym. - Forward-declare OpenVINO C types in OpenvinoApi.h instead of including headers, so there is no build-time SDK dependency at all. - Thread-safe lazy loading via std::call_once in ensure_loaded(). - OPENVINO_LIB_PATH env var for explicit library path override. - Backend always registers via static initializer (zero cost); actual OpenVINO loading deferred to first is_available()/init() call. - No changes to portable_lib.py needed — no RTLD_GLOBAL, no separate .so, no auditwheel workarounds. The backend is statically linked into _portable_lib.so like XNNPACK and has no NEEDED entries for any OpenVINO library. - Enabled on all Linux architectures (x86_64 and aarch64) since the backend has no build-time dependency and the openvino pip package supports both. ExecuTorch builds wheels for both platforms. Robustness: - LOAD_SYM macro zeros ov_ struct on partial failure to prevent dangling function pointers. - Bounds check on execute() args (ET_CHECK_OR_RETURN_ERROR). - Allocator null check with proper cleanup on failure. - Device string safely constructed from CompileSpec buffer with trailing null byte stripping. - Tensor rank validated against 1024 upper bound. - create_ov_tensor uses RAII (unique_ptr) for heap dims allocation. - Detailed comments on OpenVINO shared_ptr tensor ownership and destroy() lifecycle constraints. User experience: pip install executorch # XNNPACK+QNN+OpenVINO registered pip install executorch[openvino] # + openvino runtime, backend activates Differential Revision: D97202714

Copilot

Pull request overview

This PR reworks the OpenVINO backend runtime to remove any build-time dependency on the OpenVINO SDK by dynamically loading the OpenVINO C API (libopenvino_c.so) via dlopen/dlsym, and wires the backend into Linux wheel builds plus user-facing docs and CI smoke tests.

Changes:

Replaced the OpenVINO runtime implementation to use the OpenVINO C API via runtime symbol loading (no OpenVINO headers/libs needed at build time).
Enabled building and packaging the openvino_backend target in the pip wheel build flow and added an executorch[openvino] extra.
Updated docs/README and wheel smoke tests to reflect backend availability/registration.

Reviewed changes

Copilot reviewed 13 out of 13 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
tools/cmake/preset/pybind.cmake	Adds an overridable preset option for `EXECUTORCH_BUILD_OPENVINO`.
setup.py	Auto-enables OpenVINO backend on Linux builds and adds `openvino_backend` build target when enabled.
pyproject.toml	Adds `executorch[openvino]` optional dependency with a pinned OpenVINO version range on Linux.
docs/source/build-run-openvino.md	Adds quick-start instructions for using the pip wheel with OpenVINO runtime.
backends/openvino/runtime/OpenvinoBackend.h	Switches handle/types to OpenVINO C API pointers and adds lazy-loader state.
backends/openvino/runtime/OpenvinoBackend.cpp	Implements `dlopen`/`dlsym` loading, C API execution path, and updated type conversions/tensor wrapping.
backends/openvino/runtime/OpenvinoApi.h	Introduces forward declarations and function-pointer table for the OpenVINO C API.
backends/openvino/README.md	Documents pip-wheel quick start, env vars, and updated runtime file layout.
backends/openvino/CMakeLists.txt	Removes `find_package(OpenVINO)` and links only `executorch_core` + `dl` for runtime loading.
README-wheel.md	Updates wheel documentation to mention OpenVINO backend presence and extra install.
.ci/scripts/wheel/test_linux_aarch64.py	Adds smoke assertion that `OpenvinoBackend` is registered.
.ci/scripts/wheel/test_linux.py	Adds smoke assertion that `OpenvinoBackend` is registered (alongside QNN check).
.ci/scripts/wheel/pre_build_script.sh	Installs OpenVINO Python package on Linux in wheel CI pre-step.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

setup.py

.ci/scripts/wheel/pre_build_script.sh

backends/openvino/runtime/OpenvinoBackend.cpp

README-wheel.md

Summary: Rewrite the OpenVINO backend runtime to use dlopen/dlsym with the OpenVINO C API, eliminating the build-time dependency on the OpenVINO SDK. This follows the QNN backend's proven pattern: the backend links statically into _portable_lib.so with zero external library dependencies and loads libopenvino_c.so at runtime via dlopen when the user has the openvino pip package installed. Key design decisions: - Use OpenVINO C API (openvino/c/openvino.h) instead of C++ API to enable dlopen with dlsym function pointers. The C++ class-based API (ov::Core, ov::InferRequest) cannot be resolved via dlsym. - Forward-declare OpenVINO C types in OpenvinoApi.h instead of including headers, so there is no build-time SDK dependency at all. - Thread-safe lazy loading via std::call_once in ensure_loaded(). - OPENVINO_LIB_PATH env var for explicit library path override. - Backend always registers via static initializer (zero cost); actual OpenVINO loading deferred to first is_available()/init() call. - No changes to portable_lib.py needed — no RTLD_GLOBAL, no separate .so, no auditwheel workarounds. The backend is statically linked into _portable_lib.so like XNNPACK and has no NEEDED entries for any OpenVINO library. - Enabled on all Linux architectures (x86_64 and aarch64) since the backend has no build-time dependency and the openvino pip package supports both. ExecuTorch builds wheels for both platforms. Robustness: - LOAD_SYM macro zeros ov_ struct on partial failure to prevent dangling function pointers. - Bounds check on execute() args (ET_CHECK_OR_RETURN_ERROR). - Allocator null check with proper cleanup on failure. - Device string safely constructed from CompileSpec buffer with trailing null byte stripping. - Tensor rank validated against 1024 upper bound. - create_ov_tensor uses RAII (unique_ptr) for heap dims allocation. - Detailed comments on OpenVINO shared_ptr tensor ownership and destroy() lifecycle constraints. User experience: pip install executorch # XNNPACK+QNN+OpenVINO registered pip install executorch[openvino] # + openvino runtime, backend activates Differential Revision: D97202714

Copilot

Pull request overview

Copilot reviewed 13 out of 13 changed files in this pull request and generated 4 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

.ci/scripts/wheel/test_linux_aarch64.py

backends/openvino/runtime/OpenvinoBackend.cpp

.ci/scripts/wheel/test_linux.py

Copilot

Pull request overview

Copilot reviewed 13 out of 13 changed files in this pull request and generated 2 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

backends/openvino/runtime/OpenvinoBackend.cpp

docs/source/build-run-openvino.md

Summary: Rewrite the OpenVINO backend runtime to use dlopen/dlsym with the OpenVINO C API, eliminating the build-time dependency on the OpenVINO SDK. This follows the QNN backend's proven pattern: the backend links statically into _portable_lib.so with zero external library dependencies and loads libopenvino_c.so at runtime via dlopen when the user has the openvino pip package installed. Key design decisions: - Use OpenVINO C API (openvino/c/openvino.h) instead of C++ API to enable dlopen with dlsym function pointers. The C++ class-based API (ov::Core, ov::InferRequest) cannot be resolved via dlsym. - Forward-declare OpenVINO C types in OpenvinoApi.h instead of including headers, so there is no build-time SDK dependency at all. - Thread-safe lazy loading via std::call_once in ensure_loaded(). - OPENVINO_LIB_PATH env var for explicit library path override. - Backend always registers via static initializer (zero cost); actual OpenVINO loading deferred to first is_available()/init() call. - No changes to portable_lib.py needed — no RTLD_GLOBAL, no separate .so, no auditwheel workarounds. The backend is statically linked into _portable_lib.so like XNNPACK and has no NEEDED entries for any OpenVINO library. - Enabled on all Linux architectures (x86_64 and aarch64) since the backend has no build-time dependency and the openvino pip package supports both. ExecuTorch builds wheels for both platforms. Robustness: - LOAD_SYM macro zeros ov_ struct on partial failure to prevent dangling function pointers. - Bounds check on execute() args (ET_CHECK_OR_RETURN_ERROR). - Allocator null check with proper cleanup on failure. - Device string safely constructed from CompileSpec buffer with trailing null byte stripping. - Tensor rank validated against 1024 upper bound. - create_ov_tensor uses RAII (unique_ptr) for heap dims allocation. - Detailed comments on OpenVINO shared_ptr tensor ownership and destroy() lifecycle constraints. - std::call_once loading documented as one-shot (no retry on failure). User experience: pip install executorch # XNNPACK+QNN+OpenVINO registered pip install executorch[openvino] # + openvino runtime, backend activates Differential Revision: D97202714

Copilot

Pull request overview

Copilot reviewed 13 out of 13 changed files in this pull request and generated 2 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

extension/pybindings/portable_lib.py

backends/openvino/CMakeLists.txt

Summary: Rewrite the OpenVINO backend runtime to use dlopen/dlsym with the OpenVINO C API, eliminating the build-time dependency on the OpenVINO SDK. This follows the QNN backend's proven pattern: the backend links statically into _portable_lib.so with zero external library dependencies and loads libopenvino_c.so at runtime via dlopen when the user has the openvino pip package installed. Key design decisions: - Use OpenVINO C API (openvino/c/openvino.h) instead of C++ API to enable dlopen with dlsym function pointers. The C++ class-based API (ov::Core, ov::InferRequest) cannot be resolved via dlsym. - Forward-declare OpenVINO C types in OpenvinoApi.h instead of including headers, so there is no build-time SDK dependency at all. - Thread-safe lazy loading via std::call_once in ensure_loaded(). - OPENVINO_LIB_PATH env var for explicit library path override. - Backend always registers via static initializer (zero cost); actual OpenVINO loading deferred to first is_available()/init() call. - No changes to portable_lib.py needed — no RTLD_GLOBAL, no separate .so, no auditwheel workarounds. The backend is statically linked into _portable_lib.so like XNNPACK and has no NEEDED entries for any OpenVINO library. - Enabled on all Linux architectures (x86_64 and aarch64) since the backend has no build-time dependency and the openvino pip package supports both. ExecuTorch builds wheels for both platforms. Robustness: - LOAD_SYM macro zeros ov_ struct on partial failure to prevent dangling function pointers. - Bounds check on execute() args (ET_CHECK_OR_RETURN_ERROR). - Allocator null check with proper cleanup on failure. - Device string safely constructed from CompileSpec buffer with trailing null byte stripping. - Tensor rank validated against 1024 upper bound. - create_ov_tensor uses RAII (unique_ptr) for heap dims allocation. - Detailed comments on OpenVINO shared_ptr tensor ownership and destroy() lifecycle constraints. - std::call_once loading documented as one-shot (no retry on failure). User experience: pip install executorch # XNNPACK+QNN+OpenVINO registered pip install executorch[openvino] # + openvino runtime, backend activates Differential Revision: D97202714

Copilot

Pull request overview

Copilot reviewed 13 out of 13 changed files in this pull request and generated 5 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

pyproject.toml

.ci/scripts/wheel/test_linux_aarch64.py

extension/pybindings/portable_lib.py

backends/openvino/runtime/OpenvinoBackend.cpp

backends/openvino/README.md

Summary: Rewrite the OpenVINO backend runtime to use dlopen/dlsym with the OpenVINO C API, eliminating the build-time dependency on the OpenVINO SDK. This follows the QNN backend's proven pattern: the backend links statically into _portable_lib.so with zero external library dependencies and loads libopenvino_c.so at runtime via dlopen when the user has the openvino pip package installed. Key design decisions: - Use OpenVINO C API (openvino/c/openvino.h) instead of C++ API to enable dlopen with dlsym function pointers. The C++ class-based API (ov::Core, ov::InferRequest) cannot be resolved via dlsym. - Forward-declare OpenVINO C types in OpenvinoApi.h instead of including headers, so there is no build-time SDK dependency at all. - Thread-safe lazy loading via std::call_once in ensure_loaded(). - OPENVINO_LIB_PATH env var for explicit library path override. - Backend always registers via static initializer (zero cost); actual OpenVINO loading deferred to first is_available()/init() call. - No changes to portable_lib.py needed — no RTLD_GLOBAL, no separate .so, no auditwheel workarounds. The backend is statically linked into _portable_lib.so like XNNPACK and has no NEEDED entries for any OpenVINO library. - Enabled on all Linux architectures (x86_64 and aarch64) since the backend has no build-time dependency and the openvino pip package supports both. ExecuTorch builds wheels for both platforms. Robustness: - LOAD_SYM macro zeros ov_ struct on partial failure to prevent dangling function pointers. - Bounds check on execute() args (ET_CHECK_OR_RETURN_ERROR). - Allocator null check with proper cleanup on failure. - Device string safely constructed from CompileSpec buffer with trailing null byte stripping. - Tensor rank validated against 1024 upper bound. - create_ov_tensor uses RAII (unique_ptr) for heap dims allocation. - Detailed comments on OpenVINO shared_ptr tensor ownership and destroy() lifecycle constraints. - std::call_once loading documented as one-shot (no retry on failure). User experience: pip install executorch # XNNPACK+QNN+OpenVINO registered pip install executorch[openvino] # + openvino runtime, backend activates Differential Revision: D97202714

Copilot

Pull request overview

Copilot reviewed 13 out of 13 changed files in this pull request and generated 2 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

backends/openvino/CMakeLists.txt

extension/pybindings/portable_lib.py

Copilot AI review requested due to automatic review settings March 19, 2026 06:35

shoumikhin requested review from kirklandsign, larryliu0820 and mergennachin as code owners March 19, 2026 06:35

meta-cla bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Mar 19, 2026

meta-codesync bot added fb-exported meta-exported labels Mar 19, 2026

Copilot AI reviewed Mar 19, 2026

View reviewed changes

shoumikhin added the ciflow/trunk label Mar 19, 2026

meta-codesync bot changed the title ~~Add OpenVINO backend to pip wheel for Linux x86_64~~ Add OpenVINO backend to pip wheel for Linux x86_64 (#18309) Mar 19, 2026

shoumikhin force-pushed the export-D97202714 branch from d6de3b1 to e6675bc Compare March 19, 2026 06:54

Copilot AI review requested due to automatic review settings March 19, 2026 07:01

shoumikhin force-pushed the export-D97202714 branch from e6675bc to 48541fc Compare March 19, 2026 07:01

shoumikhin force-pushed the export-D97202714 branch from 48541fc to 4c53cb6 Compare March 19, 2026 07:05

Copilot AI reviewed Mar 19, 2026

View reviewed changes

pyproject.toml Outdated Show resolved Hide resolved

docs/source/build-run-openvino.md Show resolved Hide resolved

shoumikhin force-pushed the export-D97202714 branch from 4c53cb6 to 727ca1d Compare March 19, 2026 07:19

Copilot AI review requested due to automatic review settings March 19, 2026 20:12

shoumikhin force-pushed the export-D97202714 branch from 727ca1d to 33555f8 Compare March 19, 2026 20:12

Copilot started reviewing on behalf of shoumikhin March 19, 2026 20:12 View session

shoumikhin force-pushed the export-D97202714 branch from 33555f8 to c1be61d Compare March 19, 2026 20:18

Copilot AI reviewed Mar 19, 2026

View reviewed changes

shoumikhin force-pushed the export-D97202714 branch from 1847067 to 34e1bed Compare March 20, 2026 07:23

Copilot AI review requested due to automatic review settings March 20, 2026 07:57

shoumikhin force-pushed the export-D97202714 branch from 34e1bed to 4bfd459 Compare March 20, 2026 07:57

Copilot started reviewing on behalf of shoumikhin March 20, 2026 07:57 View session

Copilot AI reviewed Mar 20, 2026

View reviewed changes

.ci/scripts/wheel/test_linux_aarch64.py Show resolved Hide resolved

backends/openvino/runtime/OpenvinoBackend.cpp Show resolved Hide resolved

backends/openvino/runtime/OpenvinoBackend.cpp Show resolved Hide resolved

.ci/scripts/wheel/test_linux.py Show resolved Hide resolved

shoumikhin force-pushed the export-D97202714 branch from 4bfd459 to d2aaf34 Compare March 20, 2026 08:17

shoumikhin added the ciflow/binaries label Mar 20, 2026

Copilot AI review requested due to automatic review settings March 20, 2026 08:21

shoumikhin force-pushed the export-D97202714 branch from d2aaf34 to 269339c Compare March 20, 2026 08:21

Copilot started reviewing on behalf of shoumikhin March 20, 2026 08:21 View session

Copilot AI reviewed Mar 20, 2026

View reviewed changes

backends/openvino/runtime/OpenvinoBackend.cpp Show resolved Hide resolved

docs/source/build-run-openvino.md Show resolved Hide resolved

shoumikhin force-pushed the export-D97202714 branch from 269339c to 4bf9301 Compare March 20, 2026 14:40

Copilot AI review requested due to automatic review settings March 20, 2026 15:13

shoumikhin force-pushed the export-D97202714 branch from 4bf9301 to 1d7f8c9 Compare March 20, 2026 15:13

shoumikhin requested a review from JacobSzwejbka as a code owner March 20, 2026 15:13

Copilot started reviewing on behalf of shoumikhin March 20, 2026 15:14 View session

Copilot AI reviewed Mar 20, 2026

View reviewed changes

extension/pybindings/portable_lib.py Outdated Show resolved Hide resolved

backends/openvino/CMakeLists.txt Show resolved Hide resolved

shoumikhin force-pushed the export-D97202714 branch from 1d7f8c9 to a77a56e Compare March 20, 2026 15:35

Copilot AI review requested due to automatic review settings March 20, 2026 15:49

Copilot started reviewing on behalf of shoumikhin March 20, 2026 15:49 View session

Copilot AI reviewed Mar 20, 2026

View reviewed changes

shoumikhin force-pushed the export-D97202714 branch from c07dc73 to 0903b88 Compare March 20, 2026 16:55

Merge branch 'main' into export-D97202714

ae0e8d4

Copilot AI review requested due to automatic review settings March 20, 2026 16:57

Copilot started reviewing on behalf of shoumikhin March 20, 2026 16:58 View session

Copilot AI reviewed Mar 20, 2026

View reviewed changes

backends/openvino/CMakeLists.txt Show resolved Hide resolved

extension/pybindings/portable_lib.py Show resolved Hide resolved

Merge branch 'main' into export-D97202714

2e6308c

Conversation

shoumikhin commented Mar 19, 2026 • edited by meta-codesync bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot bot commented Mar 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18309

❌ 7 New Failures, 5 Cancelled Jobs, 3 Unrelated Failures

Uh oh!

meta-codesync bot commented Mar 19, 2026

Uh oh!

github-actions bot commented Mar 19, 2026

This PR needs a release notes: label

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

shoumikhin commented Mar 19, 2026 •

edited by meta-codesync bot

Loading

pytorch-bot bot commented Mar 19, 2026 •

edited

Loading

This PR needs a `release notes:` label