| Port details |
- py-onnxruntime Cross-platform, high performance ML inferencing & training accelerator
- 1.27.0_3 misc
 =0      Package not present on quarterly.This port was created during this quarter. It will be in the next quarterly branch but not the current one. - Maintainer: yuri@FreeBSD.org
- Port Added: 2026-07-03 06:33:11
- Last Update: 2026-08-22 22:39:55
- Commit Hash: 95a580e
- License: MIT
- WWW:
- https://onnxruntime.ai/
- https://github.com/microsoft/onnxruntime
- Description:
- ONNX Runtime is a cross-platform inference and training machine-learning
accelerator.
ONNX Runtime inference can enable faster customer experiences and lower costs,
supporting models from deep learning frameworks such as PyTorch and
TensorFlow/Keras as well as classical machine learning libraries such as
scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different
hardware, drivers, and operating systems, and provides optimal performance by
leveraging hardware accelerators where applicable alongside graph optimizations
and transforms.
ONNX Runtime training can accelerate the model training time on multi-node
NVIDIA GPUs for transformer models with a one-line addition for existing PyTorch
training scripts.
  ¦  ¦  ¦  ¦ 
- Manual pages:
- FreshPorts has no man page information for this port.
- pkg-plist: as obtained via:
make generate-plist - There is no configure plist information for this port.
- USE_RC_SUBR (Service Scripts)
- no SUBR information found for this port
- Dependency lines:
-
- ${PYTHON_PKGNAMEPREFIX}onnxruntime>0:misc/py-onnxruntime@${PY_FLAVOR}
- Conflicts:
- CONFLICTS_BUILD:
- abseil
- benchmark
- nsync
- googletest
- dlpack
- flatbuffers
- gsl
- mimalloc
- nlohmann-json
- onnx
- protobuf
- psimd
- pthreadpool
- pybind11
- re2
- To install the port:
- cd /usr/ports/misc/py-onnxruntime/ && make install clean
- To add the package, run one of these commands:
- pkg install misc/py-onnxruntime
- pkg install py312-onnxruntime
NOTE: If this package has multiple flavors (see below), then use one of them instead of the name specified above.
NOTE: This is a Python port. Instead of py312-onnxruntime listed in the above command, you can pick from the names under the Packages section.- PKGNAME: py312-onnxruntime
- Package flavors (<flavor>: <package>)
- distinfo:
- TIMESTAMP = 1783043785
SHA256 (onnxruntime/20250814.0.zip) = b2bdcf6682d8cb53df365bcc5d6c318a22e55821d9978a10fdb61404c026daff
SIZE (onnxruntime/20250814.0.zip) = 3194036
Packages (timestamps in pop-ups are UTC):
- Dependencies
- NOTE: FreshPorts displays only information on required and default dependencies. Optional dependencies are not covered.
- Build dependencies:
-
- cmake : devel/cmake-core
- py312-packaging>=0 : devel/py-packaging@py312
- py312-setuptools>=0 : devel/py-setuptools@py312
- py312-wheel>=0 : devel/py-wheel@py312
- py312-numpy>=1.21.6 : math/py-numpy@py312
- python3.12 : lang/python312
- py312-installer>=0 : devel/py-installer@py312
- Test dependencies:
-
- python3.12 : lang/python312
- Runtime dependencies:
-
- py312-numpy>=1.21.6 : math/py-numpy@py312
- py312-packaging>=0 : devel/py-packaging@py312
- py312-protobuf>=4.25.8 : devel/py-protobuf@py312
- py312-flatbuffers>=0 : devel/py-flatbuffers@py312
- python3.12 : lang/python312
- This port is required by:
- for Run
-
- databases/py-chromadb
- misc/py-insightface
- misc/py-sagemaker-serve
- sysutils/py-magika
- textproc/py-docling
- textproc/py-docling-demo
- textproc/py-docling-enhanced-onnx
Configuration Options:- No options to configure
- Options name:
- misc_py-onnxruntime
- USES:
- compiler:c++17-lang python
- FreshPorts was unable to extract/find any pkg message
- Master Sites:
|
Number of commits found: 6
| Commit History - (may be incomplete: for full details, see links to repositories near top of page) |
| Commit | Credits | Log message |
|---|
1.27.0_3
22 Aug 2026 22:39:55
 |
Michael Osipov (michaelo) |
misc/py-onnxruntime: Fix wheel missing the compiled pybind extension
setup.py's per-platform "libs" list decides which capi/ files get bundled
into the wheel as package data. It has dedicated branches for Linux
(manylinux and non-manylinux), Darwin, and Windows, but none for FreeBSD --
which silently fell through to the Windows-oriented default, whose *.dll/
*.pyd glob patterns never match anything here. The wheel built without
error, but ended up missing onnxruntime_pybind11_state.so entirely, along
with libonnxruntime_providers_shared.so and the versioned libonnxruntime.so;
the port previously worked around this with a manual post-install step that
copied the pybind extension in from the raw build tree afterward.
Add a FreeBSD branch to setup.py's libs list, mirroring the already-working
Darwin one (plain package-data entries, no ext_modules), so the wheel now
includes the same compiled artifacts on FreeBSD as it does on every other (Only the first 15 lines of the commit message are shown above  ) |
1.27.0_2
15 Aug 2026 15:19:50
|
Michael Osipov (michaelo) |
misc/py-onnxruntime: Fix dist site name
A typo in a dist site name caused a dist file fail to download. |
1.27.0_1
07 Aug 2026 05:09:29
|
Yuri Victorovich (yuri) |
misc/py-onnxruntime: Fix Python module
It wasn't properly installed before. |
1.27.0
02 Aug 2026 07:09:17
|
Piotr Kubaj (pkubaj) |
misc/py-onnxruntime: fix build on powerpc64le
/wrkdirs/usr/ports/misc/py-onnxruntime/work-py312/build/Release/_deps/eigen3-src/unsupported/Eigen/CXX11/../../../Eigen/src/Core/arch/AltiVec/PacketMath.h:119:35:
error: 'vec_lvsl' is deprecated: use assignment for unaligned little endian
loads/stores [-Werror,-Wdeprecated-declarations] |
1.27.0
09 Jul 2026 00:58:24
|
Yuri Victorovich (yuri) |
misc/py-onnxruntime: Add USE_PYTHON=pep517 |
1.27.0
03 Jul 2026 06:31:10
|
Yuri Victorovich (yuri) |
misc/py-onnxruntime: New port: Cross-platform, high performance ML inferencing &
training accelerator |
Number of commits found: 6
|
As an Amazon Associate I earn from qualifying purchases.