Triton Inference Server Release 22.04

The Triton Inference Server container image, release 22.04, 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.

For the list of what the container includes, refer to Deep Learning Frameworks Support Matrix.

Driver Requirements

Release 22.04 is based on NVIDIA CUDA® 11.6.2, which requires NVIDIA Driver release 510 or later. However, if you are running on a Data Center GPU (for example, T4 or any other Tesla board), use NVIDIA driver release 418.40 (or later R418), 440.33 (or later R440), 450.51 (or later R450), 460.27 (or later R460), or 470.57 (or later R470). The CUDA driver's compatibility package only supports specific drivers. For a complete list of supported drivers, see CUDA Application Compatibility. For more information, see CUDA Compatibility and Upgrades and NVIDIA CUDA and Drivers Support.

GPU Requirements

Release 22.04 supports CUDA compute capability 6.0 and later. This corresponds to GPUs in the NVIDIA Pascal, NVIDIA Volta™, NVIDIA Turing™, and NVIDIA Ampere Architecture GPU families. For a list of GPUs to which this compute capability corresponds, 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.

  • You can now specify a customized temp directory with the --tmp-dir argument to build.py during the container build.
  • You can now send a raw binary request to eliminate the need for the inference heder specification.
  • Ensembles now recognize optional inputs.
  • You can now add custom metrics to the existing Triton metrics endpoint in their custom backends and applications using the Triton C API. Documentation can be found here.
  • Official support for multiple cloud repositories.

    This support includes the same and different cloud storage providers, for example an instance of Triton can load models from two S3 buckets, two GCS buckets, and two Azure Storage containers.

  • ONNX Runtime backend now uses execution providers when available when autocomplete is enabled.

    This enhancement fixes the previous behavior where the backend always used the CPU execution provider.

  • The build.py and compose.py now support PyTorch and TensorFlow 1 backends for the CPU-only builds.
  • Refer to the 22.04 column of the Frameworks Support Matrix for container image versions on which the 22.04 inference server container is based.

NVIDIA Triton Inference Server Container Versions

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

Known Issues

Here are the known issues in this release:
  • Triton PIP wheels for ARM SBSA are not available from PyPI and pip will install an incorrect Jetson version of Triton for ARM SBSA.

    The correct wheel file can be pulled directly from the ARM SBSA SDK image and manually installed.

  • Traced models in PyTorch seem to create overflows when int8 tensor values are transformed to int32 on the GPU.

    Refer to pytorch/pytorch#66930 for more information.

  • Triton cannot retrieve GPU metrics with MIG-enabled GPU devices (A100 and A30).
  • Triton metrics might not work if the host machine is running a separate DCGM agent on bare-metal or in a container.
  • 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:

    pytorch/pytorch#27902

  • Starting in 22.02, the Triton container, which uses the 22.04 PyTorch container, will report an error during model loading in the PyTorch backend when using scripted models that were exported in the legacy format (using our 19.09 or previous PyTorch NGC containers corresponding to PyTorch 1.2.0 or previous releases).

    To successfully load the model in Triton, you need to export the model again by using a recent version of PyTorch.

  • Starting in 22.04, Model Analyzer will not sort results correctly when running analysis. To work around this issue, re-profile on main (or an earlier version) and then re-run the analysis step.