how to build custom plugins on Win10 with cuda10

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Hi, I create a new plugin layer which was successfully build on Ubuntu 18.04 cuda10, but how can I build it on Win10? Is there a CMakeLists.txt can help me build on Win10? Thank you!

2

Hi,

TRT support C++ APIs on Windows.
Please refer below link for plugin creation using C++ APIs:
https://docs.nvidia.com/deeplearning/sdk/tensorrt-archived/tensorrt-601/tensorrt-developer-guide/index.html#add_custom_layer
https://github.com/NVIDIA/TensorRT/tree/release/6.0/samples/opensource/samplePlugin

Thanks

3

Hi，SunilJB, thank you for your quick reply. But my problem is how to rebuild nvinfer_plugin.dll on win10, I have already built success libnvinfer_plugin.so in Ubuntu.

Thanks

4

Hi,

You don’t need to build the nvinfer_plugin.dll, just link the nvinfer_plugin.dll.

Thanks