Package Details: tensorrt 7.2.1.6-1

Git Clone URL: https://aur.archlinux.org/tensorrt.git (read-only, click to copy)
Package Base: tensorrt
Description: A platform for high-performance deep learning inference using NVIDIA hardware
Upstream URL: https://github.com/NVIDIA/TensorRT/
Keywords: ai artificial intelligence nvidia
Licenses: custom, Apache
Submitter: dbermond
Maintainer: dbermond
Last Packager: dbermond
Votes: 6
Popularity: 0.155008
First Submitted: 2018-07-29 16:17
Last Updated: 2020-10-21 17:33

Pinned Comments

dbermond commented on 2020-07-25 19:37

In order to build the package, you need to manually download the TensorRT file from NVIDIA's website (registration required). Place the downloaded file in the PKGBUILD directory and run makepkg.

Download website:

https://developer.nvidia.com/tensorrt/

Latest Comments

1 2 Next › Last »

dbermond commented on 2020-10-06 18:14

@gsiolas cuda 11.1 broke this package. The nvidia pre-compiled binary files depends on libraries from cuda 11.0. Reverting to use only the pre-compiled files without without building the open source components (as it was made before) will not work because there would still be pre-compiled binary files linking to cuda 11.0 libraries. Workaround is to usa cuda 11.0 if you are willing to, or wait for nvidia to release a tensorrt version that supports cuda 11.1.

gsiolas commented on 2020-10-06 17:03

Hi, I am getting the following error:

/usr/bin/ld: /home/giorgos/Projects/tensorrt/src/TensorRT-7.2.0.14/lib/libnvinfer_plugin.so: undefined reference to `nvrtcAddNameExpression@libnvrtc.so.11.0' collect2: error: ld returned 1 exit status

any idea? thx

laudney commented on 2020-07-29 20:15

The package builds perfectly. It was completely amateurish mistake on my part. I had anaconda env activated which messed up all the PATHs. Thank you.

dbermond commented on 2020-07-29 18:47

@laudney I cannot see any reasons that may be causing your build failure. The package is building fine here, either by a normal makepkg command and also by building in a clean chroot with devtools. So everything is fine.

But by hearing you say that it cannot find libraries at the standard /usr/lib path (libcudnn.so) and that it cannot find headers at the standard /usr/include path, it looks like that something is really wrong with your system. These paths are standard ones for building on Arch Linux and do not need any additional configuration.

laudney commented on 2020-07-29 09:39

It also can't find cudnn.h out of the box, which exists under /usr/include

laudney commented on 2020-07-29 09:12

@dbermond, Archlinux, makepkg -i

below libraries are not found in the linking stage:

libcublas.so.11 libcudnn.so.8 libnvrtc.so.11.0

all of these are verified to have been installed on my system

Thanks

dbermond commented on 2020-07-28 23:36

@laudney Package is building fine. What's your operating system and what's the command that you're using to build?

laudney commented on 2020-07-28 21:24

When building, it fails to find headers for cudnn under /usr/include and cuBLAS libraries under /opt/cuda/lib64

dbermond commented on 2020-07-25 19:37

In order to build the package, you need to manually download the TensorRT file from NVIDIA's website (registration required). Place the downloaded file in the PKGBUILD directory and run makepkg.

Download website:

https://developer.nvidia.com/tensorrt/

dbermond commented on 2020-03-12 16:12

@sl1pkn07 This approach should not be used on PKGBUILDs. It's not makepkg task to to create symbolic links of missing source files.

It's user responsibility to correctly place the sources files in $startdir or in $SRCDEST.