# Extending `polygraphy run` to support `trtexec`
## Introduction
`polygraphy run` allows you to run inference with multiple backends, including TensorRT and ONNX-Runtime, and compare outputs.
This extension adds support to run inference with `trtexec`.
## Installation
Follow the steps below to install the extension module. After installation, you should see the `trtexec` options in the help
output of `polygraphy run`:
1. Build using `setup.py`:
```bash
python3 setup.py bdist_wheel
```
2. Install the wheel: The wheel is installed in the `dist` directory. Install the wheel by running the following command
```
python3 -m pip install dist/polygraphy_trtexec-*.whl \
--extra-index-url https://pypi.ngc.nvidia.com
```
*NOTE: You may have to update the above command to install the appropriate version of the wheel*
3. After the installation, you can run it on the trtexec backend by using the `--trtexec` flag as follows:
```bash
polygraphy run sample.onnx --trtexec
```
Raw data
{
"_id": null,
"home_page": "https://github.com/NVIDIA/TensorRT/tree/main/tools/Polygraphy",
"name": "polygraphy-trtexec",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "",
"author": "NVIDIA",
"author_email": "svc_tensorrt@nvidia.com",
"download_url": "",
"platform": null,
"description": "# Extending `polygraphy run` to support `trtexec`\n\n## Introduction\n\n`polygraphy run` allows you to run inference with multiple backends, including TensorRT and ONNX-Runtime, and compare outputs.\nThis extension adds support to run inference with `trtexec`.\n\n## Installation\n\nFollow the steps below to install the extension module. After installation, you should see the `trtexec` options in the help\noutput of `polygraphy run`:\n\n1. Build using `setup.py`:\n\n ```bash\n python3 setup.py bdist_wheel\n ```\n\n2. Install the wheel: The wheel is installed in the `dist` directory. Install the wheel by running the following command \n ```\n python3 -m pip install dist/polygraphy_trtexec-*.whl \\\n --extra-index-url https://pypi.ngc.nvidia.com\n ```\n *NOTE: You may have to update the above command to install the appropriate version of the wheel*\n\n3. After the installation, you can run it on the trtexec backend by using the `--trtexec` flag as follows:\n\n ```bash\n polygraphy run sample.onnx --trtexec\n ```\n\n\n",
"bugtrack_url": null,
"license": "Apache 2.0",
"summary": "Polygraphy Trtexec: Extension to run on trtexec backend",
"version": "0.0.9",
"project_urls": {
"Homepage": "https://github.com/NVIDIA/TensorRT/tree/main/tools/Polygraphy"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "8ea16818433f497b43eb890131c5f4fdb41ee808809a91510fbce5812156563a",
"md5": "2d7e1e8963ab245ac0124c684c7792ef",
"sha256": "823b03c6582230cb77afd4550b69d2ef5d078cdd783cea58e66f184b84b7b02a"
},
"downloads": -1,
"filename": "polygraphy_trtexec-0.0.9-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2d7e1e8963ab245ac0124c684c7792ef",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 17300,
"upload_time": "2023-08-24T00:41:05",
"upload_time_iso_8601": "2023-08-24T00:41:05.354356Z",
"url": "https://files.pythonhosted.org/packages/8e/a1/6818433f497b43eb890131c5f4fdb41ee808809a91510fbce5812156563a/polygraphy_trtexec-0.0.9-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-08-24 00:41:05",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "NVIDIA",
"github_project": "TensorRT",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "polygraphy-trtexec"
}
JSON
