Inference Server Release 18.06 Beta
The NVIDIA container image of the Inference Server, release 18.06, 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) 7.1.4
- NCCL 2.2.13 (optimized for NVLink™ )
- TensorRT 4.0.1
Key Features and Enhancements
This Inference Server release includes the following key features and
enhancements.
- The Inference Server container image version 18.06 is based on NVIDIA Inference Server 0.3.0 beta, TensorFlow 1.8.0, and Caffe2 0.8.1.
- Support added for Caffe2 NetDef models.
- Support added for CPU-only servers in addition to servers that have one or more GPUs. The Inference Server can simultaneously use both CPUs and GPUs for inferencing.
- Logging format and control is unified across all inferencing backends: TensorFlow, TensorRT, and Caffe2.
- Gracefully exits upon receiving SIGTERM or SIGINT. Any in-flight inferences are allowed to complete before exiting, subject to a timeout.
- Server status is enhanced to report the readiness and availability of the server and of each model (and model version).
- Ubuntu 16.04 with May 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.