We are working on this and will provide an update soon.

from tensorrt.

Here is my installation steps for TX2 with a JetPack 4.3:

Build commands

git clone https://github.com/nvidia/TensorRT TensorRT
cd TensorRT
git checkout 19.12
git submodule update --init --recursive
mkdir -p build && cd build
cmake -DCUBLASLT_LIB=/usr/local/cuda-10.0/targets/aarch64-linux/lib/libcublas.so -DCUDNN_VERSION=7.6 -DCUDA_VERSION=10.0 -DPROTOBUF_VERSION=3.8.0 -DGPU_ARCHS=62 ..
CC=aarch64-linux-gnu-gcc make -j8
CC=aarch64-linux-gnu-gcc make install
cp ../parsers/onnx/NvOnnxParserTypedefs.h ../include

System wide installation commands

sudo cp ../lib/* /usr/lib/aarch64-linux-gnu
sudo cp ../include/* /usr/include/aarch64-linux-gnu
sudo cp ../bin/onnx2trt /usr/bin/
sudo cp ../bin/trtexec /usr/bin/

from tensorrt.

There is a new release. Is there any progress on this issue?

from tensorrt.