Inference Server Release 18.05 Beta
The NVIDIA container image of the Inference Server, release 18.05, is available as a beta release.
Contents of the Inference Server
This container image contains the Inference Server executable in /opt/inference_server.
The container also includes the following:
- Ubuntu 16.04
- NVIDIA CUDA 9.0.176 (see Errata section and 2.1) including CUDA® Basic Linear Algebra Subroutines library™ (cuBLAS) 9.0.333 (see section 2.3.1)
- NVIDIA CUDA® Deep Neural Network library™ (cuDNN) 7.1.2
- NCCL 2.1.15 (optimized for NVLink™ )
- TensorRT 3.0.4
Key Features and Enhancements
This Inference Server release includes the following key features and
enhancements.
- The Inference Server container image version 18.05 is based on NVIDIA Inference Server 0.2.0 beta and TensorFlow 1.7.0.
- Multiple model support. The Inference Server can manage any number and mix of TensorFlow to TensorRT models (limited by system disk and memory resources).
- TensorFlow to TensorRT integrated model support. The Inference Server can manage TensorFlow models that have been optimized with TensorRT.
- Multi-GPU support. The Inference Server can distribute inferencing across all system GPUs. Systems with heterogeneous GPUs are supported.
- Multi-tenancy support. Multiple models (or multiple instances of the same model) can run simultaneously on the same GPU.
- Batching support
- Ubuntu 16.04 with April 2018 updates
Known Issues
This is a beta release of the Inference Server. All features are expected to be available, however, some aspects of functionality and performance will likely be limited compared to a non-beta release.