TensorRT-LLM issue while installing in jetson orin nano developer kit

Robotics & Edge Computing Jetson & Embedded Systems Jetson Orin Nano
,
1

hi,
i am trying to install tensorRT in jetson orin nano developer kit,but i always get error telling subprocess-exited-with-error.
May I know the answer for this.

A clear and concise description of the bug or issue.

Environment

TensorRT Version:
GPU Type:
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered
2

Hi @jsanjana127 I’m moving this to the Jetson Orin Nano forum, where the team there should be able to help you. Can you share more logs from the install? Thanks!

Sophie

4

Hi,

Could you share the command you use and the corresponding error log with us?
Thanks.

5

hi
i have followed the below given github link.
https://github.com/NVIDIA/TensorRT-LLM/blob/v0.12.0-jetson/README4Jetson.md

the error which i get is
CMake Error at CMakeLists.txt:186 (message):
No CUDA compiler found

– Configuring incomplete, errors occurred!
See also “/home/san-jetson-orin/TensorRT-LLM/cpp/build/CMakeFiles/CMakeOutput.log”.
See also “/home/san-jetson-orin/TensorRT-LLM/cpp/build/CMakeFiles/CMakeError.log”.
Traceback (most recent call last):
File “/home/san-jetson-orin/TensorRT-LLM/scripts/build_wheel.py”, line 412, in
main(**vars(args))
File “/home/san-jetson-orin/TensorRT-LLM/scripts/build_wheel.py”, line 201, in main
build_run(
File “/usr/lib/python3.10/subprocess.py”, line 526, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command ‘cmake -DCMAKE_BUILD_TYPE=“Release” -DBUILD_PYT=“ON” -DBUILD_PYBIND=“ON” -DNVTX_DISABLE=“ON” -DBUILD_MICRO_BENCHMARKS=OFF “-DCMAKE_CUDA_ARCHITECTURES=87” “-DENABLE_MULTI_DEVICE=0” -DCMAKE_CXX_COMPILER_LAUNCHER=ccache -DCMAKE_CUDA_COMPILER_LAUNCHER=ccache -S “/home/san-jetson-orin/TensorRT-LLM/cpp”’ returned non-zero exit status 1.
Defaulting to user installation because normal site-packages is not writeable
WARNING: Requirement 'build/tensorrt_llm-.whl’ looks like a filename, but the file does not exist
ERROR: tensorrt_llm-.whl is not a valid wheel filename.

6

Hi,

Please try $ nvcc --version to verify the CUDA compiler.
If it doesn’t work, please run the below command and try it again.

$ export PATH=/usr/local/cuda-12.6/bin:$PATH
$ export LD_LIBRARY_PATH=/usr/local/cuda-12.6/lib64:$LD_LIBRARY_PATH

Thanks.