Support Matrix#

These support matrices provide an overview of the supported platforms, features, and hardware capabilities of the TensorRT APIs, parsers, and layers.

Features for Platforms and Software#

List of Supported Features per Platform#
Software	Linux x86-64	Windows x64	Linux SBSA	JetPack
Software	10.9.x	10.9.x	10.9.x	10.7.x
NVIDIA CUDA	12.8 update 1 12.6 update 3 [2] 12.5 update 1 [2] 12.4 update 1 [2] 12.3 update 2 [2] 12.2 update 2 [2] 12.1 update 1 [2] 12.0 update 1 [2] 11.8 11.7 update 1 [1] 11.6 update 2 [1] 11.5 update 2 [1] 11.4 update 4 [1] 11.3 update 1 [1] 11.2 update 2 [1] 11.1 update 1 [1] 11.0 update 3 [1]	12.8 update 1 12.6 update 3 [2] 12.5 update 1 [2] 12.4 update 1 [2] 12.3 update 2 [2] 12.2 update 2 [2] 12.1 update 1 [2] 12.0 update 1 [2] 11.8 11.7 update 1 [1] 11.6 update 2 [1] 11.5 update 2 [1] 11.4 update 4 [1] 11.3 update 1 [1] 11.2 update 2 [1] 11.1 update 1 [1] 11.0 update 3 [1]	12.8 update 1	12.6 update 3
NVIDIA cuDNN (Optional)	8.9.7	8.9.7	8.9.7	8.9.6
TensorRT Python API	Yes	Yes	Yes	Yes
NvOnnxParser	Yes	Yes	Yes	Yes
Loops	Yes	Yes	Yes	Yes

Note

Serialized engines are not portable across platforms.
If a serialized engine was created using the version-compatible flag, it could run with newer versions of TensorRT within the same major version.
If a serialized engine was created with hardware compatibility mode enabled, it can run on more than one kind of GPU architecture; the specifics depend on the hardware compatibility level used. Otherwise, serialized engines are not portable across devices.

Refer to the minimum compatible driver versions in the NVIDIA CUDA Release Notes for specific NVIDIA Driver versions.

Hardware and Precision#

The following table lists NVIDIA hardware and the precision modes each hardware supports. TensorRT has been compiled to support all NVIDIA hardware with SM 7.5 or higher capability. The table also lists the availability of DLA on this hardware. Refer to the following tables for the specifics.

Supported Hardware#
CUDA Compute Capability	Example Devices	TF32	FP32	FP16	FP8	FP4	BF16	INT8	FP16 Tensor Cores	INT8 Tensor Cores	DLA
12.0	NVIDIA RTX 5090	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	No
10.0	NVIDIA B200	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	No
9.0	NVIDIA H100	Yes	Yes	Yes	Yes	Yes [5]	Yes	Yes	Yes	Yes	No
9.0	NVIDIA GH200 480 GB	Yes	Yes	Yes	Yes	Yes [5]	Yes	Yes	Yes	Yes	No
8.9	NVIDIA L40S	Yes	Yes	Yes	Yes	Yes [5]	Yes	Yes	Yes	Yes	No
8.7	NVIDIA DRIVE AGX Orin	Yes	Yes	Yes	No	No	No	Yes	Yes	Yes	Yes
8.6	NVIDIA A10	Yes	Yes	Yes	No	No	Yes	Yes	Yes	Yes	No
8.0	NVIDIA A100	Yes	Yes	Yes	No	No	Yes	Yes	Yes	Yes	No
7.5	NVIDIA T4	No	Yes	Yes	No	No	No	Yes	Yes	Yes	No

Compute Capability Per Platform#

The section lists the supported computing capability based on the platform.

Compute Capability per Platform#
Platform	Compute Capability
Linux x86-64	7.5 8.0 8.6 [3] 8.9 [4] 9.0 [4] 10.0 [6] 12.0 [6]
Windows 10 x64	7.5 8.0 8.6 [3] 8.9 [4] 9.0 [4] 10.0 [6] 12.0 [6]
Ubuntu 24.04 SBSA	7.5 8.0 8.6 9.0 10.0 12.0
NVIDIA JetPack AArch64	8.7

Software Versions Per Platform#

List of Supported Platforms Per Software Version#
Platform	Compiler Version	Python Version
Ubuntu 20.04 x86-64	gcc 11.2.1	3.8
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	3.8
Rocky Linux 9.3 x86-64	gcc 11.2.1	3.9
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 8.4	3.12
NVIDIA JetPack AArch64	gcc 11.4	3.10

Note

The Debian or RPM packages support the Python version listed in the table. Python versions 3.8, 3.9, 3.10, 3.11, 3.12, and 3.13 are supported using Python wheel files from the tar or zip packages.

ONNX Operator Support#

The ONNX operator support list for TensorRT can be found here.

Footnotes