Comments (8)
I fixed the original problem by adding c++11
flags in demo/BERT/CMakeLists.txt
cmake_minimum_required(VERSION 3.8 FATAL_ERROR)
project(cmake_and_cuda LANGUAGES CXX CUDA)
add_compile_options(-std=c++11)
...
from tensorrt.
@ginn24
sudo ln -s TensorRT-5.1.5.0/lib/libnvinfer.so /usr/lib/libnvinfer.so
from tensorrt.
Could you share the procedure to see this output?
I could build this with the following steps. (ubuntu)
$ git clone -b release/5.1 https://github.com/nvidia/TensorRT TensorRT
$ cd TensorRT
$ git submodule update --init --recursive
$ export TRT_SOURCE=pwd
$ docker build -f docker/ubuntu-18.04.Dockerfile --build-arg CUDA_VERSION=10.1 --tag=tensorrt .
$ docker run --rm -ti --runtime=nvidia tensorrt
(docker)# git clone -b release/5.1 https://github.com/nvidia/TensorRT TensorRT
(docker)# cd TensorRT
(docker)# git submodule update --init --recursive
(docker)# export TRT_SOURCE=pwd
(docker)# mkdir -p TensorRT/demo/BERT/build
(docker)# cd TensorRT/demo/BERT/build
(docker)# cmake ..
(docker)# make -j
from tensorrt.
@haanjack Thank you. However, there are some problems.
-
The same error came out when I changed the docker build option to ubuntu-16.04 + Cuda 10.0 or centos-7. + Cuda 10.0
-
That error came out when I installed CUDA 10.1 and changed build option to ubuntu 18.04 and CUDA 10.1
/usr/bin/ld: cannot find -lnvinfer
collect2: error: ld returned 1 exit status
CMakeFiles/sample_bert.dir/build.make:85: recipe for target 'sample_bert' failed
make[2]: *** [sample_bert] Error 1
CMakeFiles/Makefile2:73: recipe for target 'CMakeFiles/sample_bert.dir/all' failed
make[1]: *** [CMakeFiles/sample_bert.dir/all] Error 2
Makefile:83: recipe for target 'all' failed
make: *** [all] Error 2
from tensorrt.
You can install TensorRT and set LD_LIBRARY_PATH.
https://blog.csdn.net/zong596568821xp/article/details/86077553
from tensorrt.
@sboschang I've already installed TensorRT but to install OSS component makes some error
from tensorrt.
The original error seems to be missing c++11
flags? I have the same error.
from tensorrt.
Warnings and errors look like missing C++11 flag, @Meteorix's solution looks right to me.
from tensorrt.
Related Issues (20)
- My onnx file successfully run by CUDAExecutionProvider, but failed with TensorrtExecutionProvider through onnxruntime HOT 6
- How to count the time spent on each operator with trtexec HOT 4
- trtexec: onnx to tensorRT convertion fails with --fp16, It reported a Segmentation fault. HOT 17
- Support ubuntu 24.04? HOT 2
- [FEATURE REQUEST] Support onnx's local function as custom plugin HOT 1
- Which Visual Studio 2022 BuildTools MSVC is the best version for Cuda 11.8 and Cuda 12.4 and so HOT 1
- add_matrix_multiple result is different from add_fully_comnected HOT 1
- Build TensorRT statically HOT 4
- Initialization failure of TensorRT 8.5.1.7 when running bcdu model on GPU A5000 HOT 10
- Cuda MEMCPY failure with float16 of TensorRT 10.3 Custom Plugin when running inference on H100 NVL x 2 HOT 1
- ICudaEngine.getTensorShape function gets the output dimension of the model that contains -1. HOT 16
- TensorRT 10.3 load custom plugin library failed. HOT 5
- Error Code 1: Cuda Driver (context is destroyed) CUDA_ERROR_CONTEXT_IS_DESTROYED HOT 4
- [Issue still exists in TRT 10.4] Fail to build the engine if input tensor number > 2^31 HOT 8
- How to build trtexec in Windows 11? HOT 1
- Abnormal of onnx model to trt model in the inference results HOT 3
- [graphShapeAnalyzer.cpp::checkCalculationStatusSanity::1916] Error Code 2: Internal Error (Assertion !isInFlight(p.second.symbolicRep) failed. ) HOT 2
- Engine can NOT be shared if model uses dynamic shape. HOT 9
- Does tensorrt 7.2.2.3 has python wheel ? HOT 4
- python error in colab: module 'tensorrt' has no attribute '__version__' HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorrt.