TensorRT Inference Server Container Release Notes :: Deep Learning SDK Documentation

TensorRT Inference Server Container Release Notes (PDF) - Last updated October 1, 2018 -

TensorRT inference server Release 18.07 Beta

The NVIDIA container image of the TensorRT inference server, release 18.07, is available as a beta release.

Contents of the TensorRT inference server

This container image contains the TensorRT inference server executable in /opt/inference_server.

The container also includes the following:

Ubuntu 16.04
Note: Container image 18.07-py2 contains Python 2.7; 18.07-py3 contains Python 3.5.
NVIDIA CUDA 9.0.176 (see Errata section and 2.1) including CUDA^® Basic Linear Algebra Subroutines library™ (cuBLAS) 9.0.425
NVIDIA CUDA^® Deep Neural Network library™ (cuDNN) 7.1.4
NCCL 2.2.13 (optimized for NVLink™ )
TensorRT 4.0.1

Driver Requirements

Release 18.07 is based on CUDA 9, which requires NVIDIA Driver release 384.xx.

Key Features and Enhancements

This TensorRT inference server release includes the following key features and enhancements.

The TensorRT inference server container image version 18.07 is based on NVIDIA Inference Server 0.4.0 Beta and TensorFlow 1.8.0 and Caffe2 0.8.1.
Latest version of CUDA^® Basic Linear Algebra Subroutines library™ (cuBLAS) 9.0.425.
Support added for TensorFlow SavedModel format.
Support added for gRPC in addition to existing HTTP REST.
Ubuntu 16.04 with June 2018 updates

Known Issues

There are no known issues in this release.