Is this page helpful?

TensorRT 10.15.1 Support Matrix#

What’s New in This Support Matrix#

This release includes the following platform and tooling updates:

Platform and Software Changes

CUDA Support

  • Added support for CUDA 13.1 update 1 on Linux x86-64, Windows x64, and Linux SBSA platforms

  • CUDA 13.x builds are now distributed separately from CUDA 12.x builds for better compatibility

Python Version Updates

  • Rocky Linux 8.9: Updated from Python 3.8 → Python 3.12

  • Rocky Linux 9.3: Updated from Python 3.9 → Python 3.12

  • This change aligns with Python 3.9 end-of-life and improves compatibility with upstream PyPI packages

New Platform Support

  • Added Debian 12 SBSA platform support with gcc 11.4 and Python 3.11

  • Added compute capability 8.9 support for Ubuntu 24.04 SBSA platform

Note

These updates reflect the announcements in the 10.15.1 Release Notes, particularly the Python packaging changes for improved ecosystem compatibility.

Platform and Software Support#

The following table shows TensorRT component support across different platforms, including supported CUDA versions, cuDNN, Python API, ONNX parser, and control flow features.

Important

Engine Portability

  • Platform: Serialized engines are not portable across platforms (Linux, Windows, etc.).

  • Version Compatibility: Engines built with the version-compatible flag can run with newer TensorRT versions within the same major version.

  • Hardware Compatibility: Engines built with hardware compatibility mode can run on multiple GPU architectures, depending on the hardware compatibility level used. Without this mode, engines are not portable across different GPU architectures.

Driver Requirements: Refer to the NVIDIA CUDA Release Notes for minimum compatible NVIDIA Driver versions.

Component

Linux x86-64 (10.15.x)

Windows x64 (10.15.x)

Linux SBSA (10.15.x)

NVIDIA JetPack (10.7.x)

NVIDIA CUDA

13.1 update 1

12.6 update 3

NVIDIA cuDNN (Optional)

8.9.7

8.9.7

N/A

8.9.6

TensorRT Python API

Supported

Supported

Supported

Supported

ONNX Parser

Supported

Supported

Supported

Supported

Control Flow (Loops)

Supported

Supported

Supported

Supported

GPU Architecture and Precision Support#

The following table shows supported precision modes for each NVIDIA GPU architecture. TensorRT supports NVIDIA hardware with compute capability SM 7.5 or higher. The table also indicates Deep Learning Accelerator (DLA) availability.

CUDA Compute Capability

Example Devices

TF32

FP32

FP16

FP8

FP4

BF16

INT8

DLA

12.1

NVIDIA DGX Spark

Supported

Supported

Supported

Supported

Supported

Supported

Supported

N/A

12.0

NVIDIA RTX PRO 6000 Blackwell

Supported

Supported

Supported

Supported

Supported

Supported

Supported

N/A

11.0

NVIDIA Jetson AGX Thor

Supported

Supported

Supported

Supported

Supported

Supported

Supported

N/A

10.3

NVIDIA B300

Supported

Supported

Supported

Supported

Supported

Supported

Supported

N/A

10.0

NVIDIA B200

Supported

Supported

Supported

Supported

Supported

Supported

Supported

N/A

9.0

  • NVIDIA H100

  • NVIDIA GH200 480 GB

Supported

Supported

Supported

Supported

Supported [3]

Supported

Supported

N/A

8.9

NVIDIA L40S

Supported

Supported

Supported

Supported

Supported [3]

Supported

Supported

N/A

8.7

NVIDIA DRIVE AGX Orin

Supported

Supported

Supported

N/A

N/A

N/A

Supported

Supported

8.6

NVIDIA A10

Supported

Supported

Supported

N/A

N/A

Supported

Supported

N/A

8.0

NVIDIA A100

Supported

Supported

Supported

N/A

N/A

Supported

Supported

N/A

7.5

NVIDIA T4

N/A

Supported

Supported

N/A

N/A

N/A

Supported

N/A

Supported Compute Capabilities#

The following table shows which GPU compute capabilities are supported on each platform.

Platform

Compute Capability

Linux x86-64

  • 7.5

  • 8.0

  • 8.6

  • 8.9

  • 9.0

  • 10.0 [4]

  • 10.3 [5]

  • 12.0 [4]

Windows 10 x64

  • 7.5

  • 8.0

  • 8.6

  • 8.9

  • 9.0

  • 10.0 [4]

  • 10.3 [5]

  • 12.0 [4]

Ubuntu 24.04 SBSA

  • 7.5

  • 8.0

  • 8.6

  • 8.9

  • 9.0

  • 10.0

  • 10.3

  • 11.0

  • 12.0

  • 12.1

NVIDIA JetPack AArch64

8.7

Compiler and Python Requirements#

The following table shows the required compiler and Python versions for building and using TensorRT on each supported platform.

Platform

Compiler Version

Python Version

Ubuntu 22.04 x86-64

gcc 11.2.1

3.10

Ubuntu 24.04 x86-64

gcc 11.2.1

3.12

Rocky Linux 8.9 x86-64

gcc 11.2.1

3.12

Rocky Linux 9.3 x86-64

gcc 11.2.1

3.12

Debian 12 x86-64

gcc 11.2.1

3.11

SLES 15 x86-64

gcc 11.2.1

N/A

  • Windows 10 x64

  • Windows 11 x64

  • Windows Server 2022 x64

MSVC 2019 v16.9.2

N/A

Ubuntu 24.04 SBSA

gcc 11.4

3.12

Debian 12 SBSA

gcc 11.4

3.11

NVIDIA JetPack AArch64

gcc 11.4

3.12

Note

Python Version Support

  • Debian/RPM packages: Support the Python version listed in the table for each platform.

  • Wheel packages (tar/zip): Support Python 3.8, 3.9, 3.10, 3.11, 3.12, and 3.13 across all platforms.

ONNX Operator Support#

TensorRT provides extensive ONNX operator support through the ONNX parser. The complete and up-to-date ONNX operator support list for TensorRT is available in the ONNX-TensorRT Operator Support documentation.

Footnotes