Triton Inference Server Release 21.05

The Triton Inference Server container image, release 21.05, is available on NGC and is open source on GitHub.

Contents of the Triton Inference Server container

The Triton Inference Server Docker image contains the inference server executable and related shared libraries in /opt/tritonserver.

The container also includes the following:

Driver Requirements

Release 21.05 is based on NVIDIA CUDA 11.3.0, which requires NVIDIA Driver release 465.19.01 or later. However, if you are running on Data Center GPUs (formerly Tesla), for example, T4, you may use NVIDIA driver release 418.40 (or later R418), 440.33 (or later R440), 450.51 (or later R450), or 460.27 (or later R460). 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 and NVIDIA CUDA and Drivers Support.

GPU Requirements

Release 21.05 supports CUDA compute capability 6.0 and higher. This corresponds to GPUs in the NVIDIA Pascal, Volta, Turing, and Ampere Architecture GPU 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

This Inference Server release includes the following key features and enhancements.

  • Triton on Jetson now supports ONNX via the ONNX Runtime backend.
  • The Triton server and HTTP clients (Python and C++) now support compression.
  • Ragged batching is now supported for ONNX models.
  • The Triton clients have moved to a separate repo: https://github.com/triton-inference-server/client
  • Trace now correctly reports all timestamps for all backends.
  • NVTX annotations are fixed.
  • The legacy custom backend support is removed. All custom backends must be implemented using the TRITONBACKEND API described here: https://github.com/triton-inference-server/backend.
  • Added CLI subcommands in Model Analyzer for profile, analyze, and report. See CLI documentation for usage instructions.
  • Model Analyzer can create a detailed report of any specific model configuration with the report subcommand.
  • CPU only mode is supported in Model Analyzer.
  • Refer to the 21.05 column of the Frameworks Support Matrix for container image versions that the 21.05 inference server container is based on.
  • Ubuntu 20.04 with April 2021 updates.

NVIDIA Triton Inference Server Container Versions

The following table shows what versions of Ubuntu, CUDA, Triton Inference Server, and TensorRT are supported in each of the NVIDIA containers for Triton Inference Server. For older container versions, refer to the Frameworks Support Matrix.

Container Version Triton Inference Server Ubuntu CUDA Toolkit TensorRT
21.05 2.10.0 20.04 NVIDIA CUDA 11.3.0 TensorRT 7.2.3.4
21.04 2.9.0
21.03 2.8.0 NVIDIA CUDA 11.2.1 TensorRT 7.2.2.3
21.02 2.7.0 NVIDIA CUDA 11.2.0 TensorRT 7.2.2.3+cuda11.1.0.024
20.12 2.6.0 NVIDIA CUDA 11.1.1 TensorRT 7.2.2
20.11 2.5.0

18.04

 NVIDIA CUDA 11.1.0 TensorRT 7.2.1
20.10 2.4.0
20.09 2.3.0 NVIDIA CUDA 11.0.3 TensorRT 7.1.3
20.08

2.2.0
20.07 1.15.0

2.1.0

 NVIDIA CUDA 11.0.194
20.06 1.14.0

2.0.0

 NVIDIA CUDA 11.0.167 TensorRT 7.1.2
20.03.1 1.13.0 NVIDIA CUDA 10.2.89 TensorRT 7.0.0
20.03 1.12.0

20.02

20.01

 1.11.0
1.10.0

19.12

19.11

 1.9.0 TensorRT 6.0.1
1.8.0
19.10 1.7.0 NVIDIA CUDA 10.1.243
19.09 1.6.0
19.08 1.5.0 TensorRT 5.1.5

Known Issues

  • Triton’s TensorRT support depends on the input-consumed feature of TensorRT. In some rare cases using TensorRT 8.0 and earlier versions, the input-consumed event fires earlier than expected, causing Triton to overwrite input tensors while they are still in use and leading to corrupt input data being used for inference. This situation occurs when the inputs feed directly into a TensorRT layer that is optimized into a ForeignNode in the builder log. If you encounter accuracy issues with your TensorRT model, you can work around the issue by enabling the output_copy_stream option in your model’s configuration (https://github.com/triton-inference-server/common/blob/main/protobuf/model_config.proto#L816).
  • Running a PyTorch TorchScript model using the PyTorch backend, where multiple instances of a model are configured can lead to a slowdown in model execution due to the following PyTorch issue: https://github.com/pytorch/pytorch/issues/27902.
  • Compared with the 21.02 and earlier releases, there are backwards incompatible changes in the example Python client shared-memory support library when that library is used for tensors of type BYTES. The utils.serialize_byte_tensor() and utils.deserialize_byte_tensor() functions now return np.object_ numpy arrays where previously they returned np.bytes_ numpy arrays. Code depending on np.bytes_ must be updated. This change was necessary because the np.bytes_ type removes all trailing zeros from each array element and so binary sequences ending in zero(s) could not be represented with the old behavior. Correct usage of the Python client shared-memory support library is shown inhttps://github.com/triton-inference-server/server/blob/r21.03/src/clients/python/examples/simple_http_shm_string_client.py.