Tensorrt 8.0.0.3 with cuda 11.1

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

Description

when trying to run an executable with tensorrt can’t use the shared library libnvinfer due to:

error while loading shared libraries: libnvrtc.so.11.2: cannot open shared object file: No such file or directory

I’ve installed tensort RT through TAR file through this link:
https://developer.nvidia.com/compute/machine-learning/tensorrt/secure/8.0/tars/tensorrt-8.0.0.3.linux.x86_64-gnu.cuda-11.3.cudnn8.2.tar.gz

this is the ldd for libnvinfer.so:

linux-vdso.so.1 (0x00007ffde271e000)
libnvrtc.so.11.2 => not found
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007fe96f1e3000)
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007fe96efdf000)
libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007fe96ec56000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007fe96e8b8000)
libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007fe96e6a0000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007fe96e2af000)
/lib64/ld-linux-x86-64.so.2 (0x00007fe994d62000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007fe96e090000)

Environment

TensorRT Version: 8.0.0.3
GPU Type: GeForce RTX 3080
Nvidia Driver Version: 455.32.00
CUDA Version: 11.1
CUDNN Version: 8.1.0
Operating System + Version: ubuntu 18.4

2

Hi ,
We recommend you to check the supported features from the below link.

You can refer below link for all the supported operators list.
For unsupported operators, you need to create a custom plugin to support the operation

Thanks!

7

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.