hello, I want to use tensorrt serving.
first, as my server os has no nvidia driver version more then 410, I run docker pull nvcr.io/nvidia/tensorrtserver:18.08-py2, then I run nvidia-docker run --rm --shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 -p8000:8000 -p8001:8001 -p8002:8002 -v/xxx/model_repository:/models nvcr.io/nvidia/tensorrt:18.08-py2 trtserver --model-store=/models, but it shows error:
=====================
== NVIDIA TensorRT ==
=====================
NVIDIA Release 18.08 (build 601781)
NVIDIA TensorRT 4.0.1 (c) 2016-2018, NVIDIA CORPORATION. All rights reserved.
Container image (c) 2018, NVIDIA CORPORATION. All rights reserved.
https://developer.nvidia.com/tensorrt
To install python sample dependencies, run /opt/tensorrt/python/python_setup.sh
/usr/local/bin/nvidia_entrypoint.sh: line 33: exec: trtserver: not found
I can not find nvidia_entrypoint.sh under the dir /usr/local/bin,
how to fix it?
Linux distro and version:
LSB Version: :core-4.1-amd64:core-4.1-noarch
Distributor ID: CentOS
Description: CentOS Linux release 7.4.1708 (Core)
Release: 7.4.1708
Codename: Core
other envirs:
GPU type: Tesla v100
nvidia driver version: NVIDIA-SMI 396.44
CUDA version: 9.0
CUDNN version: 7.3.0
Python version [if using python]: python2.7
TensorRT version: 5.0.2.6
gcc>5.3/lib64