Triton Inference Server Release 23.12

The Triton Inference Server container image, release 23.12, 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 a complete list of what the container includes, refer to Deep Learning Frameworks Support Matrix.

The container also includes the following:

Driver Requirements

Release 23.12 is based on CUDA 12.3.2, which requires NVIDIA Driver release 545 or later. However, if you are running on a data center GPU (for example, T4 or any other data center GPU), you can use NVIDIA driver release 450.51 (or later R450), 470.57 (or later R470), 510.47 (or later R510), or 525.85 (or later R525) 535.86 (or later R535), or 545.23 (or later R545).

The CUDA driver's compatibility package only supports particular drivers. Thus, users should upgrade from all R418, R440, R460, and R520 drivers, which are not forward-compatible with CUDA 12.3. For a complete list of supported drivers, see the CUDA Application Compatibility topic. For more information, see CUDA Compatibility and Upgrades.

GPU Requirements

Release 23.12 supports CUDA compute capability 6.0 and later. This corresponds to GPUs in the NVIDIA Pascal, NVIDIA Volta™, NVIDIA Turing™, NVIDIA Ampere architecture, NVIDIA Hopper™, and NVIDIA Ada Lovelace architecture 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.

  • Added metrics support to TRTLLM backend when running within Triton.
  • Request ID will be included in opentelemetry tracing.
  • For Jetson devices which support Jetpack 6.0 and above, Triton now publishes containers, based on the latest version of Jetpack, on NGC with the suffix “-igpu”. These containers are:
    • XX.YY-py3-igpu: Much like the XX.YY-py3 container, this contains tritonserver and all supported backends for Jetson devices.
    • XX.YY-py3-sdk-igpu: Much like the XX.YY-py3-sdk container, this contains the Tritonclient and Triton Tools supported on Jetson devices.
  • For Jetson devices which support Jetpack 5.1.2, an image has been included in this release that backports a CVE patch for the Triton model load API. This image is based off the r23.06 release and can be built from source using the ‘r23.06-update-1-jp’ tag. Refer to the 23.12 column of theFrameworks Support Matrix for container image versions on which the 23.12 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.

Container Version Triton Inference Server Ubuntu CUDA Toolkit TensorRT
23.12 2.41 22.04 NVIDIA CUDA 12.3.2 TensorRT 8.6.1.6
23.11 2.40 NVIDIA CUDA 12.3.0
23.10 2.39.0 NVIDIA CUDA 12.2.2
23.09 2.38.0 NVIDIA CUDA 12.2.1
23.08 2.37.0
23.07 2.36.0 NVIDIA CUDA 12.1.1
23.06 2.35.0
23.05 2.34.0 TensorRT 8.6.1.2
23.04 2.33.0 20.04 NVIDIA CUDA 12.1.0 TensorRT 8.6.1
23.03 2.32.0 TensorRT 8.5.3
23.02 2.31.0 NVIDIA CUDA 12.0.1
23.01 2.30.0 TensorRT 8.5.2.2
22.12 2.29.0 NVIDIA CUDA 11.8.0 TensorRT 8.5.1
22.11 2.28.0
22.10 2.27.0 TensorRT 8.5 EA
22.09 2.26.0
22.08 2.25.0 NVIDIA CUDA 11.7.1 TensorRT 8.4.2.4
22.07 2.24.0 NVIDIA CUDA 11.7 Update 1 Preview TensorRT 8.4.1
22.06 2.23.0 TensorRT 8.2.5
22.05 2.22.0 NVIDIA CUDA 11.7.0
22.04 2.21.0 NVIDIA CUDA 11.6.2 TensorRT 8.2.4.2 and

for x86 Linux and SBSA

TensorRT 8.4.0 for JetPack/Jetson

22.03 2.20.0 NVIDIA CUDA 11.6.1 TensorRT 8.2.3 and

for x86 Linux and SBSA

TensorRT 8.4.0 for JetPack/Jetson

22.02 2.19.0 NVIDIA CUDA 11.6.0 TensorRT 8.2.3
22.01 2.18.0 TensorRT 8.2.2
21.12 2.17.0 NVIDIA CUDA 11.5.0 TensorRT 8.2.1.8
21.11 2.16.0

TensorRT 8.2.1.8 for x64 Linux

TensorRT 8.0.2.2 for ARM SBSA Linux
21.10 2.15.0 NVIDIA CUDA 11.4.2 with cuBLAS 11.6.5.2
21.09 2.14.0 NVIDIA CUDA 11.4.2 TensorRT 8.0.3
21.08 2.13.0 NVIDIA CUDA 11.4.1 TensorRT 8.0.1.6
21.07 2.12.0 NVIDIA CUDA 11.4.0
21.06.1 2.11.0 NVIDIA CUDA 11.3.1 TensorRT 7.2.3.4
21.06
21.05 2.10.0 NVIDIA CUDA 11.3.0
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

  • Reuse-grpc-port and reuse-http-port are now properly parsed as booleans. 0 and 1 will continue to work as values. Any other integers will throw an error.
  • TensorRT-LLM backend provides limited support of Triton extensions and features.
  • The TensorRT-LLM backend may core dump on server shutdown. This impacts server teardown only and will not impact inferencing.
  • When using decoupled models, there is a possibility that response order as sent from the backend may not match with the order in which these responses are received by the streaming gRPC client. Note that this only applies to responses from different requests. Any responses corresponding to the same request will still be received in their expected order, relative to each other.
  • The FasterTransformer backend is only officially supported for 22.12, though it can be built for Triton container versions up to 23.07.
  • The Java CAPI is known to have intermittent segfaults we’re looking for a root cause.
  • Some systems which implement malloc() may not release memory back to the operating system right away causing a false memory leak. This can be mitigated by using a different malloc implementation. Tcmalloc and jemalloc are installed in the Triton container and can be used by specifying the library in LD_PRELOAD. We recommend experimenting with both tcmalloc and jemalloc to determine which one works better for your use case.
  • Auto-complete may cause an increase in server start time. To avoid a start time increase, users can provide the full model configuration and launch the server with --disable-auto-complete-config.
  • Auto-complete does not support PyTorch models due to lack of metadata in the model. It can only verify that the number of inputs and the input names matches what is specified in the model configuration. There is no model metadata about the number of outputs and datatypes. Related PyTorch bug:https://github.com/pytorch/pytorch/issues/38273.
  • Triton Client PIP wheels for ARM SBSA are not available from PyPI and pip will install an incorrect Jetson version of Triton Client library for Arm SBSA. The correct client 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.
  • When cloud storage (AWS, GCS, AZURE) is used as a model repository and a model has multiple versions, Triton creates an extra local copy of the cloud model’s folder in the temporary directory, which is deleted upon server’s shutdown.
  • Model Analyzer is not able to analyze and optimize ensemble model configs due to a bug in the way composing models are loaded.