saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-14 20:48:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update onnx-tensorrt parser (#3369)

Browse source 
* sync onnx-tensorrt parser and update TensorRT doc

* remove --msvc_toolset 14.16 in tensorrt ci pipeline
This commit is contained in:
stevenlix 2020-03-30 20:31:59 -07:00 committed by GitHub
parent ce9acf0c21
commit 2332a93db0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 10 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
BUILD.md
View file

@ -176,6 +176,12 @@ See more information on the TensorRT Execution Provider [here](./docs/execution_
* The path to TensorRT installation must be provided via the `--tensorrt_home parameter`.
#### Build Instructions
##### Windows
```
.\build.bat --cudnn_home <path to cuDNN home> --cuda_home <path to CUDA home> --use_tensorrt --tensorrt_home <path to TensorRT home>
```
##### Linux
```

2
cmake/external/onnx-tensorrt vendored

@ -1 +1 @@
Subproject commit 5a7cba1a768c3bb01cbf323e3acdeb8e29e3beca
Subproject commit 8b8b89d18423cae7bb8a6a95ea346dd49a4dccc0

2
docs/execution_providers/TensorRT-ExecutionProvider.md
View file

@ -7,7 +7,7 @@ With the TensorRT execution provider, the ONNX Runtime delivers better inferenci
## Build
For build instructions, please see the [BUILD page](../../BUILD.md#tensorrt).
The TensorRT execution provider for ONNX Runtime is built and tested with TensorRT 6.0.1.5.
The TensorRT execution provider for ONNX Runtime is built and tested with TensorRT 7.0.0.11.
## Using the TensorRT execution provider
### C/C++

4
tools/ci_build/github/azure-pipelines/win-gpu-tensorrt-ci-pipeline.yml
View file

@ -42,7 +42,7 @@ jobs:
displayName: 'Generate cmake config'
inputs:
scriptPath: '$(Build.SourcesDirectory)\tools\ci_build\build.py'
arguments: '--config $(BuildConfig) --build_dir $(Build.BinariesDirectory) --skip_submodule_sync --build_shared_lib --update --cmake_generator "Visual Studio 16 2019" --msvc_toolset 14.16 --build_wheel --enable_onnx_tests --use_tensorrt --tensorrt_home="C:\local\TensorRT-7.0.0.11.cuda-10.2.cudnn7.6\TensorRT-7.0.0.11" --cuda_version=10.2 --cuda_home="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2" --cudnn_home="C:\local\cudnn-10.2-windows10-x64-v7.6.5.32\cuda" --cmake_extra_defines CMAKE_SYSTEM_VERSION=10.0.18362.0'
arguments: '--config $(BuildConfig) --build_dir $(Build.BinariesDirectory) --skip_submodule_sync --build_shared_lib --update --cmake_generator "Visual Studio 16 2019" --build_wheel --enable_onnx_tests --use_tensorrt --tensorrt_home="C:\local\TensorRT-7.0.0.11.cuda-10.2.cudnn7.6\TensorRT-7.0.0.11" --cuda_version=10.2 --cuda_home="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2" --cudnn_home="C:\local\cudnn-10.2-windows10-x64-v7.6.5.32\cuda" --cmake_extra_defines CMAKE_SYSTEM_VERSION=10.0.18362.0'
workingDirectory: '$(Build.BinariesDirectory)'
- task: VSBuild@1
@ -81,7 +81,7 @@ jobs:
del wheel_filename_file
python.exe -m pip install -q --upgrade %WHEEL_FILENAME%
set PATH=$(Build.BinariesDirectory)\$(BuildConfig)\$(BuildConfig);%PATH%
python $(Build.SourcesDirectory)\tools\ci_build\build.py --config $(BuildConfig) --build_dir $(Build.BinariesDirectory) --skip_submodule_sync --build_shared_lib --test --cmake_generator "Visual Studio 16 2019" --msvc_toolset 14.16 --build_wheel --enable_onnx_tests --use_tensorrt --tensorrt_home="C:\local\TensorRT-7.0.0.11.cuda-10.2.cudnn7.6\TensorRT-7.0.0.11" --cuda_version=10.2 --cuda_home="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2" --cudnn_home="C:\local\cudnn-10.2-windows10-x64-v7.6.5.32\cuda" --cmake_extra_defines CMAKE_SYSTEM_VERSION=10.0.18362.0
python $(Build.SourcesDirectory)\tools\ci_build\build.py --config $(BuildConfig) --build_dir $(Build.BinariesDirectory) --skip_submodule_sync --build_shared_lib --test --cmake_generator "Visual Studio 16 2019" --build_wheel --enable_onnx_tests --use_tensorrt --tensorrt_home="C:\local\TensorRT-7.0.0.11.cuda-10.2.cudnn7.6\TensorRT-7.0.0.11" --cuda_version=10.2 --cuda_home="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2" --cudnn_home="C:\local\cudnn-10.2-windows10-x64-v7.6.5.32\cuda" --cmake_extra_defines CMAKE_SYSTEM_VERSION=10.0.18362.0
workingDirectory: '$(Build.BinariesDirectory)\$(BuildConfig)\$(BuildConfig)'
displayName: 'Run tests'