ONNX Optimizer
Introduction
ONNX provides a C++ library for performing arbitrary optimizations on ONNX models, as well as a growing list of prepackaged optimization passes.
The primary motivation is to share work between the many ONNX backend implementations. Not all possible optimizations can be directly implemented on ONNX graphs - some will need additional backend-specific information - but many can, and our aim is to provide all such passes along with ONNX so that they can be re-used with a single function call.
You may be interested in invoking the provided passes, or in implementing new ones (or both).
Installation
You can install onnxoptimizer from PyPI:
pip3 install onnxoptimizer
Note that you may need to upgrade your pip first if you have trouble:
pip3 install -U pip
If you want to build from source:
git clone --recursive https://github.com/onnx/optimizer onnxoptimizer
cd onnxoptimizer
pip3 install -e .
Note that you need to install protobuf before building from source.
Command-line API
Now you can use command-line api in terminal instead of python script.
python -m onnxoptimizer input_model.onnx output_model.onnx
Arguments list is following:
# python3 -m onnxoptimizer -h
usage: python -m onnxoptimizer input_model.onnx output_model.onnx
onnxoptimizer command-line api
optional arguments:
-h, --help show this help message and exit
--print_all_passes print all available passes
--print_fuse_elimination_passes
print all fuse and elimination passes
-p [PASSES ...], --passes [PASSES ...]
list of optimization passes name, if no set, fuse_and_elimination_passes will be used
--fixed_point fixed point
Roadmap
- More built-in pass
- Separate graph rewriting and constant folding (or a pure graph rewriting mode, see issue #9 for the details)
Relevant tools
- onnx-simplifier: A handy and popular tool based on onnxoptimizer
Code of Conduct
2 maintainers
Metadata
2 maintainers
Release files for onnxoptimizer 0.4.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| onnxoptimizer-0.4.2.tar.gz | 12.1 MB | Details |
Built distributions (wheels)
Total release size: 20.2 MB
Release files / onnxoptimizer-0.4.2.tar.gz
| Download URL | onnxoptimizer-0.4.2.tar.gz |
|---|---|
| Size | 12.1 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
dac4a972b5dc80a870b930e85e4b043d090d4546d7878106ef8448e07f94622e
|
|
BLAKE2b-256 checksum How to use checksums |
5ba7e4f0e67a7e077d7cc65b968febfc53f8f52d3a22257624aa7977f14fff8c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency logRelease files / onnxoptimizer-0.4.2-cp312-abi3-win_amd64.whl
| Download URL | onnxoptimizer-0.4.2-cp312-abi3-win_amd64.whl |
|---|---|
| Size | 486.8 kB |
| Tags | CPython 3.12 Windows x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
cc85d031f35689d36d91e79770611015014c41278fd39b664c6ccc27dc045aa0
|
|
BLAKE2b-256 checksum How to use checksums |
67c1173031e8e5f9185a168209ead6f8b5e985f951a817d7b7b9c62a335a1a33
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency logRelease files / onnxoptimizer-0.4.2-cp312-abi3-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
| Download URL | onnxoptimizer-0.4.2-cp312-abi3-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 1.0 MB |
| Tags | CPython 3.12 Linux glibc 2.24+ x86-64 Linux glibc 2.28+ x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
af19ee4dd7a852a18511aeabdbe1e3c8b4dd8e02b187356965b269d480ac7147
|
|
BLAKE2b-256 checksum How to use checksums |
853ed512bf70a66f85d3d7bfc79380da24c026d6409b28c5cd48f2d91e450046
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency logRelease files / onnxoptimizer-0.4.2-cp312-abi3-macosx_10_15_universal2.whl
| Download URL | onnxoptimizer-0.4.2-cp312-abi3-macosx_10_15_universal2.whl |
|---|---|
| Size | 1.2 MB |
| Tags | CPython 3.12 abi3 macOS 10.15+ universal2 (ARM64, x86-64) |
|
SHA-256 checksum How to use checksums |
7229ffe7d54c692e4ba0a2516f94805a4f462e7fce7634e080a381fb82ec2378
|
|
BLAKE2b-256 checksum How to use checksums |
e7e9bedd490a39b5201d33aea1f2812ca74bba9b30defa66fc94e3d46878b8b8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency logRelease files / onnxoptimizer-0.4.2-cp311-cp311-win_amd64.whl
| Download URL | onnxoptimizer-0.4.2-cp311-cp311-win_amd64.whl |
|---|---|
| Size | 488.2 kB |
| Tags | CPython 3.11 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
74f5400833dbdd9439d17c0fd78b962fd2ae7a369169e41e19dd09ae532350b6
|
|
BLAKE2b-256 checksum How to use checksums |
e65a43b60c74ea2f3024340452962b0fbbf2300907d4e88e31847f4e67faa631
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency logRelease files / onnxoptimizer-0.4.2-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
| Download URL | onnxoptimizer-0.4.2-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 1.0 MB |
| Tags | CPython 3.11 Linux glibc 2.24+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
f278dc846b7144b7bdd063d0838848bdf45ce2e35d205379f169ec77deb76d9e
|
|
BLAKE2b-256 checksum How to use checksums |
cc7c99b072778f66e0f95e43874f6a2fd2b96968979e1fb644d186abbed2f2e6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency logRelease files / onnxoptimizer-0.4.2-cp311-cp311-macosx_10_15_universal2.whl
| Download URL | onnxoptimizer-0.4.2-cp311-cp311-macosx_10_15_universal2.whl |
|---|---|
| Size | 1.2 MB |
| Tags | CPython 3.11 macOS 10.15+ universal2 (ARM64, x86-64) |
|
SHA-256 checksum How to use checksums |
b6aeaf03ecfa626b2e716ce910b1547d450d4b79673ab1c446fd761c05c8dcf8
|
|
BLAKE2b-256 checksum How to use checksums |
f8f4c0eae052169bb058c847f9ed3a4c217e2a3b2f63177e370b1ee2afd2e614
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency logRelease files / onnxoptimizer-0.4.2-cp310-cp310-win_amd64.whl
| Download URL | onnxoptimizer-0.4.2-cp310-cp310-win_amd64.whl |
|---|---|
| Size | 488.1 kB |
| Tags | CPython 3.10 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
65185aa0a3629db7d6618762dfb6ec1afa19401048773318191eef7b55eb142c
|
|
BLAKE2b-256 checksum How to use checksums |
b02815ed9afb400f964cd4f1ab0bb790623d2d2a6acf755221cc717c34492b3e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency logRelease files / onnxoptimizer-0.4.2-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
| Download URL | onnxoptimizer-0.4.2-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 1.0 MB |
| Tags | CPython 3.10 Linux glibc 2.24+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
ee2ed3cc6cc08543fc542c65d49bf2a8933e185b454d576ae3cd1bc877ee858c
|
|
BLAKE2b-256 checksum How to use checksums |
389c09f01912085cd8f2c1a1bcd6d74106d85e839f0b06fc705b843086553a8e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency logRelease files / onnxoptimizer-0.4.2-cp310-cp310-macosx_10_15_universal2.whl
| Download URL | onnxoptimizer-0.4.2-cp310-cp310-macosx_10_15_universal2.whl |
|---|---|
| Size | 1.2 MB |
| Tags | CPython 3.10 macOS 10.15+ universal2 (ARM64, x86-64) |
|
SHA-256 checksum How to use checksums |
73b0859397ea1ffca6e896c6799c48933f09b16226def686264e68ef386f1239
|
|
BLAKE2b-256 checksum How to use checksums |
b7601e08c455e8262b7a8ecc2c10e586a7aaa517c0b9e3771b3c7b5ec80b6f29
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 7, 2026.
Transparency log
