Chi Lo
c86476a636
[TensorRT] adapt for TRT lib name change after TRT 10 GA (update) ( #20550 )
...
https://github.com/microsoft/onnxruntime/pull/20445
The nvonnxparser still needs major version appending to it when building
oss parser.
2024-05-06 15:00:13 -07:00
Chi Lo
a077330c3e
[TensorRT] adapt for TRT lib name change after TRT 10 GA ( #20445 )
...
For TensorRT 10 GA onwards, the TensorRT libraries will have major
version appended to the end on Windows, for example, nvinfer_10.dll,
nvinfer_plugin_10.dll, nvonnxparser_10.dll ...
Change cmake file accordingly.
2024-04-24 21:46:54 -07:00
Maximilian Müller
c20ced4132
Use CMake's find package for CUDA libs ( #19673 )
...
### Description
Answers issue #19640
More details are in the issue, basically I am changing all the include
directory and link directory usage to CMake's `CUDA::*` targets
2024-02-27 11:26:48 -08:00
Chi Lo
dfafcb58aa
[TensorRT EP] Properly set CUDA_INCLUDE_DIR for onnx-tensorrt ( #18274 )
...
https://github.com/microsoft/onnxruntime/pull/17468
The above PR didn't fully fix the issue for some environments.
This PR fixes this.
2023-11-03 20:04:10 -07:00
Chi Lo
8abaa7b753
[TensorRT EP] Fix cmake install ( #17923 )
...
We removed tensorrt_provider_factory.h in the
[PR](https://github.com/microsoft/onnxruntime/pull/17617 ).
Need to remove the copy of this file when cmake install.
2023-10-16 09:16:24 -07:00
Changming Sun
05ac9f6f2a
Split onnxruntime_providers.cmake to multiple ( #17853 )
...
### Description
Split onnxruntime_providers.cmake to multiple files, for easier editing.
No other change was made in this PR.
2023-10-09 20:33:44 -07:00
