Got error when running infer_onnx_tensorrt example #1333
Description
Environment
FastDeploy version:
fastdeploy-gpu-python 1.0.3
OS Platform:
Linux cm.bigdata 3.10.0-1160.76.1.el7.x86_64 #1 SMP Wed Aug 10 16:21:17 UTC 2022 x86_64 x86_64 x86_64 GNU/Linux
CentOS Linux release 7.9.2009 (Core)
Hardware:
Nvidia GPU RTX A4000 CUDA 11.2 CUDNN 8.2
Program Language:
Python 3.10
Problem description
When running the infer_onnx_tensorrt example
FastDeploy/examples/runtime/python/infer_onnx_tensorrt.py
Error message occur as follow:
[ERROR] fastdeploy/runtime/backends/tensorrt/trt_backend.cc(256)::InitFromOnnx [ERROR] Error occurs while calling cudaStreamCreate().