Description
Unable to install tensor rt on jetson orin.
Environment
TensorRT Version:
GPU Type: JETSON ORIN
Nvidia Driver Version:
CUDA Version: 11.4.9
CUDNN Version:
Operating System + Version: UBUNTU 20.04
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable): 2.1
Baremetal or Container (if container which image + tag):
Got the following error :
(infer) jetson@jetson:~$ python3 -m pip install torch torch-tensorrt tensorrt Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com Requirement already satisfied: torch in ./envs/infer/lib/python3.8/site-packages (2.1.0a0+41361538.nv23.6) /usr/share/python-wheels/urllib3-1.25.8-py2.py3-none-any.whl/urllib3/connectionpool.py:1004: InsecureRequestWarning: Unverified HTTPS request is being made to host 'pypi.ngc.nvidia.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings Collecting torch-tensorrt Downloading torch-tensorrt-0.0.0.post1.tar.gz (9.0 kB) ERROR: Command errored out with exit status 1: command: /home/jetson/envs/infer/bin/python3 -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/tmp/pip-install-803vkxhm/torch-tensorrt/setup.py'"'"'; __file__='"'"'/tmp/pip-install-803vkxhm/torch-tensorrt/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' egg_info --egg-base /tmp/pip-install-803vkxhm/torch-tensorrt/pip-egg-info cwd: /tmp/pip-install-803vkxhm/torch-tensorrt/ Complete output (12 lines): Traceback (most recent call last): File "<string>", line 1, in <module> File "/tmp/pip-install-803vkxhm/torch-tensorrt/setup.py", line 125, in <module> raise RuntimeError(open("ERROR.txt", "r").read()) RuntimeError: ########################################################################################### The package you are trying to install is only a placeholder project on PyPI.org repository. To install Torch-TensorRT please run the following command: $ pip install torch-tensorrt -f https://github.com/NVIDIA/Torch-TensorRT/releases ########################################################################################### ---------------------------------------- ERROR: Command errored out with exit status 1: python setup.py egg_info Check the logs for full command output. (infer) jetson@jetson:~$ pip install torch-tensorrt -f https://github.com/NVIDIA/Torch-TensorRT/releases Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com Looking in links: https://github.com/NVIDIA/Torch-TensorRT/releases /usr/share/python-wheels/urllib3-1.25.8-py2.py3-none-any.whl/urllib3/connectionpool.py:1004: InsecureRequestWarning: Unverified HTTPS request is being made to host 'pypi.ngc.nvidia.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings Collecting torch-tensorrt Downloading torch-tensorrt-0.0.0.post1.tar.gz (9.0 kB) ERROR: Command errored out with exit status 1: command: /home/jetson/envs/infer/bin/python3 -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/tmp/pip-install-0u_kx_xb/torch-tensorrt/setup.py'"'"'; __file__='"'"'/tmp/pip-install-0u_kx_xb/torch-tensorrt/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' egg_info --egg-base /tmp/pip-install-0u_kx_xb/torch-tensorrt/pip-egg-info cwd: /tmp/pip-install-0u_kx_xb/torch-tensorrt/ Complete output (12 lines): Traceback (most recent call last): File "<string>", line 1, in <module> File "/tmp/pip-install-0u_kx_xb/torch-tensorrt/setup.py", line 125, in <module> raise RuntimeError(open("ERROR.txt", "r").read()) RuntimeError: ########################################################################################### The package you are trying to install is only a placeholder project on PyPI.org repository. To install Torch-TensorRT please run the following command: $ pip install torch-tensorrt -f https://github.com/NVIDIA/Torch-TensorRT/releases ########################################################################################### ---------------------------------------- ERROR: Command errored out with exit status 1: python setup.py egg_info Check the logs for full command output. (infer) jetson@jetson:~$