Wonnx is an ONNX runtime based on wgpu aimed at being a universal GPU runtime, written in Rust.
Project description
WONNX Python module
This crate allows using WONNX from Python.
Building
To build the Python module for development:
cd wonnx-py
python3 -m venv .venv
source .venv/bin/activate
pip install maturin
maturin develop
You can also use make python
from the project root. If you want to specify a specific version of python, use:
make python PYTHON=python3.10
(e.g. if you used brew install python@3.10
to install Python 3.10 on macOS).
Testing
For testing, additional dependencies are required. First, ensure you have the protobuf compiler (protoc
) installed and
in your PATH (on macOS, you can use brew install protobuf
and possibly brew link protobuf
to install it). Nextl, install
Python dependencies:
pip install -r requirements.txt
To test a specific operator, you can use the following command:
OP_TESTED=reduce pytest tests/test_specific_op.py
To test the current set of fully tested op:
python tests/test_onnx_backend.py
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Hashes for wonnx-0.5.1-cp37-abi3-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7ebed80d38e63cbcc9211a3b48f256c45f90ca167590c51aaf08114de77ffe41 |
|
MD5 | e99ecaa14445e180c8a2f17e773624a1 |
|
BLAKE2b-256 | ec08e9da33c6113b07123058d0b1b33946f033ebd9b173e5f498992fc611f36c |
Hashes for wonnx-0.5.1-cp37-abi3-musllinux_1_2_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4c8a7abb1d59ba634735cbb1ba7d52eb8a293851d4b573f27553602f20f036de |
|
MD5 | 1444ee18a9f389b68a962ae853f52959 |
|
BLAKE2b-256 | 0b5d1a7bdf3405cfdfdc13b2520b7504742a67be931804e144ae32a43c52c7d3 |
Hashes for wonnx-0.5.1-cp37-abi3-musllinux_1_2_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 472c8000d4f0cb0299d60d7158779aef97cca9e27ace266774a46525ad5e70e9 |
|
MD5 | fb8531c72aa149ae0e6cea222b5bf9a3 |
|
BLAKE2b-256 | cba6ed5b1afbf68b8a62562d6d4a088a6aedf5731bc36572d59399467696bb65 |
Hashes for wonnx-0.5.1-cp37-abi3-musllinux_1_2_armv7l.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | aebd5a748f8f9d25e622f83855a5dfe284b99f7223f04533478a7a43e8e0e08e |
|
MD5 | c75e970e438e52a81739f1089fa40439 |
|
BLAKE2b-256 | 1a4755bebb54556ebcaf636316d01ce67db3c666d4923281b99e0ead7aff9c07 |
Hashes for wonnx-0.5.1-cp37-abi3-musllinux_1_2_aarch64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6b76f30be8f32e616288cfca1bf8d2507dbdc23ea37e93e8f4664978df346993 |
|
MD5 | 2bfc9125189c9015f6c37d873adb9475 |
|
BLAKE2b-256 | 302307edb6224c548577665cbf9587ba126097a9ebd64ca7b08c56075d134b4b |
Hashes for wonnx-0.5.1-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2dfe76738a679eee7d503dc905d5e2046b9896f019643b5422de87d1d0d1e754 |
|
MD5 | fc2422233df92e5e13ba6d3b5f3a5d07 |
|
BLAKE2b-256 | 58f525822ac9b0b4f7a7233968abf976fbe2afbd9d0327635891f2275b04e4e9 |
Hashes for wonnx-0.5.1-cp37-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 53cc5dc221763117e24d6e3d88773d2cdca98fda9859a6e556ad1ddbda1e9ca7 |
|
MD5 | cad11336ef28a948be9981ddc5c111f4 |
|
BLAKE2b-256 | 4e90f3a7ad0c4d6b5919ff721ee72a03797a8e43ec0ae5b7b246045a8f30f79d |
Hashes for wonnx-0.5.1-cp37-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d0fb195a86f347ae370622ba6a483f88461cbfef33be326e73f042db47e1ef1e |
|
MD5 | c4b7c62957a4714aad42cac4d1ef11be |
|
BLAKE2b-256 | f7d38ab149cdd3d8f6f07f454a9f9c307340a4574a81e102546e7050c7439fb5 |
Hashes for wonnx-0.5.1-cp37-abi3-manylinux_2_17_ppc64.manylinux2014_ppc64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ce5ed46e20274ead217c57461e122790f0bacd3482ba58296704d6ca3787bf7b |
|
MD5 | 057e553b81e2e0948c5c166aa350dc53 |
|
BLAKE2b-256 | 84e29b8b5a5e7fb22d66c9bae11610d10e1062013a5c3e83839e836409df1c86 |
Hashes for wonnx-0.5.1-cp37-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ac9824e5d2653a563f481fbe9b03d30a6bbf011086ef83fcb958ca228126a0c4 |
|
MD5 | f051110ff10e1c9c8d493f4de0614c19 |
|
BLAKE2b-256 | 7a1ff8cefc1420bb125a38b72c4adcd8fe6d4313bca82cbc7d79902daf7ca4b7 |
Hashes for wonnx-0.5.1-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8cad6a76d419ff9055f5db602ff84ab8bcd3766d945fa0cb336bc478dca4a0b6 |
|
MD5 | 239b4bc77232f156af0420919a0d3fb3 |
|
BLAKE2b-256 | 7b36e89ea2aafef4169717e1de3bf739ad5a3eb2828e4e12bc8117a83bb2a477 |
Hashes for wonnx-0.5.1-cp37-abi3-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a9fcd2adda00dfba4fd9b5ffabfac358eb671be1da031598e734e079d7b8bad0 |
|
MD5 | ee7dfde11203cb318c6c853792e91093 |
|
BLAKE2b-256 | f2fe71743c80bb494f938ac6651068541f8aed615705fd0ea8e59a102301367c |
Hashes for wonnx-0.5.1-cp37-abi3-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 33b7c55faefdb3ea5dfbfb8441ae797dc706310b3a7617d1fd2b996c7010ac6d |
|
MD5 | 3e4780f06cbc8aeecc48ab90bd52720f |
|
BLAKE2b-256 | f95feee4dba672061c5f9b7a08d2c40e54fd8b5974b62c327ed6dbf63819580e |
Hashes for wonnx-0.5.1-cp37-abi3-macosx_10_7_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8cbb3a7e91601ccb35990c05e7af01f2e8d2589543cdc743c6e2da26e2be8986 |
|
MD5 | cf5de8a89926d8c769639b6f0648181d |
|
BLAKE2b-256 | 7ac705485ab809de9efaaeda3ec0541d11fbead8655b39214ce796a5f1739a9d |