Triton Inference Server Release 20.01
The TensorRT Inference Server container image, release 20.01, is available on NGC and is open source on GitHub.
Contents of the Triton inference server container
The TensorRT Inference Server Docker image contains the inference server executable and related shared libraries in /opt/tensorrtserver.
- Ubuntu 18.04 including Python 3.6
- NVIDIA CUDA 10.2.89 including cuBLAS 10.2.2.89
- NVIDIA cuDNN 7.6.5
- NVIDIA NCCL 2.5.6 (optimized for NVLink™ )
- MLNX_OFED
- OpenMPI 3.1.4
- TensorRT 7.0.0
Driver Requirements
Release 20.01 is based on NVIDIA CUDA 10.2.89, which requires NVIDIA Driver release 440.33.01. However, if you are running on Tesla (for example, T4 or any other Tesla board), you may use NVIDIA driver release 396, 384.111+, 410, 418.xx or 440.30. The CUDA driver's compatibility package only supports particular drivers. For a complete list of supported drivers, see the CUDA Application Compatibility topic. For more information, see CUDA Compatibility and Upgrades.
GPU Requirements
Release 20.01 supports CUDA compute capability 6.0 and higher. This corresponds to GPUs in the Pascal, Volta, and Turing families. Specifically, for a list of GPUs that this compute capability corresponds to, see CUDA GPUs. For additional support details, see Deep Learning Frameworks Support Matrix.
Key Features and Enhancements
- Refer to the Frameworks Support Matrix for container image versions that the 20.01 inference server container is based on.
- The inference server container image version 20.01 is additionally based on ONNX Runtime 1.1.1.
- Server status can be requested in JSON format using the HTTP/REST API. Use endpoint /api/status?format=json.
- The dynamic batcher now has an option to preserve the ordering of batched requests when there are multiple model instances. See model_config.proto for more information.
- Latest version of TensorRT 7.0.0
- Ubuntu 18.04 with December 2019 updates
NVIDIA TensorRT Inference Server Container Versions
The following table shows what versions of Ubuntu, CUDA, TensorRT Inference Server, and TensorRT are supported in each of the NVIDIA containers for TensorRT Inference Server. For older container versions, refer to the Frameworks Support Matrix.
Container Version | Ubuntu | CUDA Toolkit | TensorRT Inference Server | TensorRT |
---|---|---|---|---|
20.01 |
18.04 16.04 |
NVIDIA CUDA 10.2.89 | 1.10.0 | TensorRT 7.0.0 |
1.9.0 | TensorRT 6.0.1 | |||
1.8.0 | ||||
19.10 | NVIDIA CUDA 10.1.243 | 1.7.0 | ||
19.09 | 1.6.0 | |||
19.08 | 1.5.0 | TensorRT 5.1.5 |
Known Issues
-
TensorRT reformat-free I/O is not supported.
-
Some versions of Google Kubernetes Engine (GKE) contain a regression in the handling of LD_LIBRARY_PATH that prevents the inference server container from running correctly (see issue 141255952). Use a GKE 1.13 or earlier version or a GKE 1.14.6 or later version to avoid this issue.