NVIDIA TensorRT 10.x Download
NVIDIA TensorRT is a platform for high performance deep learning inference.
TensorRT works across all NVIDIA GPUs using the CUDA platform.
Please review TensorRT online documentation for more information, including the installation guide.
Please review and accept the license agreement to proceed to download the software.
Please download the version compatible with your development environment.
Announcements
- TensorRT 11.0 is coming soon with powerful new capabilities designed to accelerate your AI inference workflows:
- Enhanced Developer Experience: Improved ease of use and seamless integration with PyTorch and Hugging Face ecosystems
- Optimized for High-Growth Workloads: Stronger performance alignment across edge, automotive, and data center deployments
- Modernized API: To streamline development, TensorRT 11.0 will remove legacy APIs including Weakly-typed APIs, Implicit INT8 quantization, IPluginV2, and TREX
- Breaking packaging changes that may require updates to your build and deployment scripts:
- Linux: trtexec and other executables are now installed to /usr/bin (previously /usr/src/tensorrt/bin/) and are added to the system PATH by default. Symlinks are provided for backward compatibility.
- Windows: TensorRT library files (*.dll) are now located under the bin subdirectory (previously lib) within the TensorRT zip package.
- Static libraries on Linux (libnvinfer_static.a, libnvonnxparser_static.a, etc.) are deprecated starting with TensorRT 10.11 and will be removed in TensorRT 11.0. Migrate to shared libraries.
- Python Packaging Changes: Python 3.9 and older have reached end-of-life. To improve Python compatibility with upstream PyPI packages and the TensorRT Python samples, the RPM packages for RHEL/Rocky Linux 8 and RHEL/Rocky Linux 9 now depend on Python 3.12.
- Platform Support: Debian 12 is supported for the Server Base System Architecture (SBSA) platform starting with the TensorRT 10.15 release.
Key features and enhancements in this TensorRT release
Transformer and LLM Optimizations
- KV Cache Reuse: Added KVCacheUpdate API to efficiently reuse KV cache and save GPU computation, significantly improving performance for transformer-based models. Built-in RoPE Support: TensorRT now includes built-in support for RoPE (Rotary Position Embedding) for transformers. This makes it easier to express RoPE and convert ONNX models with the new RotaryEmbedding API layer to TensorRT.
- Multi-Head Attention (MHA): Fixed a bug that previously prohibited users from having more than one IAttention in the INetwork.
- Dynamic Quantization Enhancements: To support Sage Attention and other models that use per token quantization, Dynamic Quantization now supports up to 2D blocks, and Quantize and Dequantize supports up to ND blocks.
DLA Enhancements
- DLA-Only Mode: A new ONNX Parser flag kREPORT_CAPABILITY_DLA has been added to generate TensorRT engines from an ONNX model that solely runs on DLA without GPU fallback, providing better deployment flexibility for DLA-targeted workloads.
ONNX Parser Improvements
- Plugin Override Control: The behavior for a TensorRT plugin sharing a name with a standard ONNX operator has been improved and a new ONNX Parser flag kENABLE_PLUGIN_OVERRIDE was introduced.
Samples and Tools
- Strongly Typed Networks Sample: A new Python sample strongly_type_autocast has been added to showcase using ModelOpt's AutoCast tool to convert a FP32 ONNX model to mixed FP32-FP16 precision, and building the engine with TensorRT's strong typing mode.
Bug Fixes and Performance
- Windows GPU Support: Support for B200 and B300 GPUs on Windows is no longer considered experimental.
- Memory Leak Fix: Fixed a host memory leak issue when building TensorRT engines on NVIDIA Blackwell GPUs.
- Fused Multi-Head Attention (MHA): Multiple pointwise inputs are now supported by the Fused MHA implementation, and fixed a bug that previously prohibited users from having more than one IAttention in the INetwork.
- Performance Optimizations on Blackwell GPUs: Fixed multiple performance regressions including:
- An up to 9% regression on B300 compared to B200 for FLUX with FP16 precision
- An up to 24% regression on GB200 for ResNext-50 FP8 models when using CUDA 13.0
- An up to 25% regression on GB200 for ConvNets with GlobalAveragePool operation like EfficientNet
- An up to 10% regression on GB200 for BERT in FP16 precision
- Python API Performance: Fixed an up to 40% performance regression with set_input_shape from Python binding.
API Changes
- To view API changes between releases, refer to the TensorRT GitHub repository and use the compare tool.
Please download the version compatible with your development environment using the links below.
Documentation
TensorRT 10.15.1 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.15.1 GA for Linux x86_64 and CUDA 12.0 to 12.9 TAR Package
- TensorRT 10.15.1 GA for Ubuntu 22.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.15.1 GA for Ubuntu 24.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.15.1 GA for Debian 12 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.15.1 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.15.1 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.15.1 GA for Linux x86_64 and CUDA 13.0 to 13.1 TAR Package
- TensorRT 10.15.1 GA for Ubuntu 22.04 and CUDA 13.0 to 13.1 DEB local repo Package
- TensorRT 10.15.1 GA for Ubuntu 24.04 and CUDA 13.0 to 13.1 DEB local repo Package
- TensorRT 10.15.1 GA for Debian 12 and CUDA 13.0 to 13.1 DEB local repo Package
- TensorRT 10.15.1 GA for RedHat / Rocky Linux 8 and CUDA 13.0 to 13.1 RPM local repo Package
- TensorRT 10.15.1 GA for RedHat / Rocky Linux 9 and CUDA 13.0 to 13.1 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.15.1 GA for Windows 10, 11, Server 2022 and CUDA 12.0 to 12.9 ZIP Package
- TensorRT 10.15.1 GA for Windows 10, 11, Server 2022 and CUDA 13.0 to 13.1 ZIP Package
TensorRT 10.15.1 GA for ARM SBSA & JetPack
Debian and TAR Install Packages for Linux
- TensorRT 10.15.1 GA for Linux SBSA and CUDA 13.1 TAR Package
- TensorRT 10.15.1 GA for Ubuntu 24.04 and CUDA 13.1 DEB local repo Package
- TensorRT 10.15.1 GA for Ubuntu 24.04 and CUDA 13.1 DEB cross local repo Package
- TensorRT 10.15.1 GA for Debian 12 and CUDA 13.1 DEB local repo Package
- TensorRT 10.15.1 GA for Debian 12 and CUDA 13.1 DEB cross local repo Package
Notable changes in this TensorRT release.
- Support for NVIDIA GB300, NVIDIA DGX B300, and NVIDIA DGX Spark have been added in this release. This TensorRT release is expected to be functionally complete and fully performant for these GPUs.
- The TensorRT package no longer includes samples and their data. Refer to the TensorRT GitHub repository to retrieve and build samples
- The API Capture and Replay tools can now be used on AArch64 platforms.
- Added API IAttention to allow users to add an attention operator that runs a fused attention kernel.
- Added SerializationFlag::kINCLUDE_REFIT to ensure that the serialized engine remains refittable. When serializing a weight-stripping engine without SerializationFlag::kEXCLUDE_WEIGHTS, the resulting serialized engine is not refittable by default.
- For the Topk, NMS, and NonZero operations, new APIs have been introduced to control the data type of the output indices, allowing users to specify whether the indices should be INT32 or INT64. Specifically, the new Topk::setIndicesType and Topk::getIndicesType (similarly for NMS and NonZero) APIs enable setting and retrieving the indices data type. Additionally, new versions of AddTopk, AddNMS, and AddNonZero APIs have been introduced with an extra parameter for specifying the indices data type..
- Enhanced multi-head attention fusions when the head size does not meet the alignment requirements by padding it automatically.
- The builder resources (libnvinfer_builder_resource.so on Linux and nvinfer_builder_resource.dll on Windows) are partitioned according to the architecture to reduce memory usage during engine build. Each partitioned builder resource contains cubins for a single architecture only. Additionally, there is a separate builder resource containing PTX code for hardware forward compatibility serialization. During engine build, only the builder resource corresponding to the architecture of the profile device is loaded.
- The number of synchronous memory allocations have been reduced for performance improvements.
- TensorRT provides an API ICudaEngine::getEngineStat() to retrieve detailed statistics about the engine, including precise weight sizes. Using the EngineStat enum, you can query the following:
- kTOTAL_WEIGHTS_SIZE: Returns the total size in bytes of all weights utilized by the engine.
- kSTRIPPED_WEIGHTS_SIZE: Returns the size in bytes of stripped weights for engines built with the BuilderFlag::kSTRIP_PLAN flag.
Please download the version compatible with your development environment using the links below.
Documentation
TensorRT 10.14.1 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.14.1 GA for Linux x86_64 and CUDA 12.0 to 12.9 TAR Package
- TensorRT 10.14.1 GA for Ubuntu 22.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.14.1 GA for Ubuntu 24.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.14.1 GA for Debian 12 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.14.1 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.14.1 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.14.1 GA for Linux x86_64 and CUDA 13.0 TAR Package
- TensorRT 10.14.1 GA for Ubuntu 22.04 and CUDA 13.0 DEB local repo Package
- TensorRT 10.14.1 GA for Ubuntu 24.04 and CUDA 13.0 DEB local repo Package
- TensorRT 10.14.1 GA for Debian 12 and CUDA 13.0 DEB local repo Package
- TensorRT 10.14.1 GA for RedHat / Rocky Linux 8 and CUDA 13.0 RPM local repo Package
- TensorRT 10.14.1 GA for RedHat / Rocky Linux 9 and CUDA 13.0 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.14.1 GA for Windows 10, 11, Server 2022 and CUDA 12.0 to 12.9 ZIP Package
- TensorRT 10.14.1 GA for Windows 10, 11, Server 2022 and CUDA 13.0 ZIP Package
TensorRT 10.14.1 GA for ARM SBSA & JetPack
Debian and TAR Install Packages for Linux
Notable changes in this TensorRT release.
- Added support for TensorRT API Capture and Replay, which streamlines the process of reproducing and debugging issues within your applications. For more information, refer to the TensorRT API Capture and Replay documentation.
- Python 3.8 no longer supports all samples and demos. Python 3.8 wheels for TensorRT will continue to be shipped.
Please download the version compatible with your development environment using the links below.
Documentation
TensorRT 10.13.3 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.13.3 GA for Linux x86_64 and CUDA 12.0 to 12.9 TAR Package
- TensorRT 10.13.3 GA for Ubuntu 22.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.13.3 GA for Ubuntu 24.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.13.3 GA for Debian 12 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.13.3 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.13.3 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.13.3 GA for Linux x86_64 and CUDA 13.0 TAR Package
- TensorRT 10.13.3 GA for Ubuntu 22.04 and CUDA 13.0 DEB local repo Package
- TensorRT 10.13.3 GA for Ubuntu 24.04 and CUDA 13.0 DEB local repo Package
- TensorRT 10.13.3 GA for Debian 12 and CUDA 13.0 DEB local repo Package
- TensorRT 10.13.3 GA for RedHat / Rocky Linux 8 and CUDA 13.0 RPM local repo Package
- TensorRT 10.13.3 GA for RedHat / Rocky Linux 9 and CUDA 13.0 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.13.3 GA for Windows 10, 11, Server 2022 and CUDA 12.0 to 12.9 ZIP Package
- TensorRT 10.13.3 GA for Windows 10, 11, Server 2022 and CUDA 13.0 ZIP Package
TensorRT 10.13.3 GA for ARM SBSA & JetPack
Debian and TAR Install Packages for Linux
Notable changes in this TensorRT release.
- The JetPack release for TensorRT has been combined with the TensorRT SBSA release starting with this TensorRT release. JetPack 7.x users should use the SBSA target and cross packages as there are no JetPack specific packages.
- This TensorRT release introduces support for CUDA 13.0. With the introduction of support for CUDA 13.x, support for CUDA 11.x has been removed starting with this TensorRT release. TensorRT supports the two most recent CUDA major versions, CUDA 12.x and 13.x in this case.
- Ubuntu 20.04 reached end-of-life (EOL) on May 31, 2025 and is no longer supported by TensorRT starting with this release.
Please download the version compatible with your development environment using the links below.
Documentation
TensorRT 10.13.2 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.13.2 GA for Linux x86_64 and CUDA 12.0 to 12.9 TAR Package
- TensorRT 10.13.2 GA for Ubuntu 22.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.13.2 GA for Ubuntu 24.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.13.2 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.13.2 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.13.2 GA for Linux x86_64 and CUDA 13.0 TAR Package
- TensorRT 10.13.2 GA for Ubuntu 22.04 and CUDA 13.0 DEB local repo Package
- TensorRT 10.13.2 GA for Ubuntu 24.04 and CUDA 13.0 DEB local repo Package
- TensorRT 10.13.2 GA for RedHat / Rocky Linux 8 and CUDA 13.0 RPM local repo Package
- TensorRT 10.13.2 GA for RedHat / Rocky Linux 9 and CUDA 13.0 RPM local repo Package
Zip Packages for Windows
TensorRT 10.13.2 GA for ARM SBSA & JetPack
Debian and TAR Install Packages for Linux
This TensorRT release includes the following key features and enhancements.
- Added the following APIs to the ONNX parser:
- IParser::loadModelProto()
- IParser::loadModelProto()
- IParser::parseModelProto()
- IParserRefitter::loadModelProto()
- IParserRefitter::loadInitializer()
- IParserRefitter::refitModelProto()
For more information, refer to the Importing a Model Using the ONNX Parser With Custom Weights section for C++ and Python APIs in the API Documentation.
- Improved Multi-Head Attention fusion and performance with two-dimensional masks on NVIDIA Blackwell GPUs with compute capability 10.0.
- Improved FP8 Multi-Head Attention performance on NVIDIA Ada Lovelace and Blackwell GPUs with compute capability 12.0.
- Enabled NVFP4 Gemm + SwiGLU fusions on Blackwell GPUs with compute capability 10.0.
Please download the version compatible with your development environment using the links below.
Documentation
TensorRT 10.13 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.13 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.13 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.13 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.13 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.13 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.13 GA for Linux x86_64 and CUDA 12.0 to 12.9 TAR Package
- TensorRT 10.13 GA for Ubuntu 20.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.13 GA for Ubuntu 22.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.13 GA for Ubuntu 24.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.13 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.13 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.9 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.13 GA for Windows 10, 11, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.13 GA for Windows 10, 11, Server 2022 and CUDA 12.0 to 12.9 ZIP Package
TensorRT 10.13 GA for ARM SBSA
Debian and TAR Install Packages for Linux
This TensorRT release includes the following key features and enhancements.
- Added support for MXFP8 quantization. Performs block quantization, quantizing across 32 high-precision elements to produce 32 quantized output values, and one E8M0 scaling factor.
- Extended the debug tensor feature to allow marking all unfused tensors as debug tensors. This does not prevent fusion optimization and makes marking easier. Supported dumping intermediate tensors in summary, NumPy, string, and raw data formats in trtexec by utilizing this feature.
- Introduced two refactored Python samples with cleaner code structure and comprehensive documentation demonstrating ONNX model conversion with performance comparison (1_run_onnx_with_tensorrt) and network construction using TensorRT Layer APIs for LSTM networks (2_construct_network_with_layer_apis).
- Introduced the independence distributive feature to support determinism across the distributive axis of output tensor, that is, if some inputs are identical across the distributive axis, the corresponding outputs are guaranteed to be identical. Refer to the Distributive Independence Determinism section for the definition of distributive axis for different layers.
Please download the version compatible with your development environment using the links below.
Documentation
TensorRT 10.12 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.12 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.12 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.12 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.12 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.12 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.12 GA for Linux x86_64 and CUDA 12.0 to 12.9 TAR Package
- TensorRT 10.12 GA for Ubuntu 20.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.12 GA for Ubuntu 22.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.12 GA for Ubuntu 24.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.12 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.12 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.9 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.12 GA for Windows 10, 11, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.12 GA for Windows 10, 11, Server 2022 and CUDA 12.0 to 12.9 ZIP Package
TensorRT 10.12 GA for ARM SBSA
Debian and TAR Install Packages for Linux
This TensorRT release includes the following key features and enhancements.
- Condition-Dependent Shapes
- The inputs to
IIfConditionalOutputLayermay now have different shapes. They must still have the same rank (number of dimensions).
- The inputs to
- Plugin enhancements include:
- Added version 2 of the DisentangledAttention plugin (
DisentangledAttention_TRT), that implements the IPluginV3 interface. The legacy version (1), that implements the IPluginV2DynamicExt interface, is maintained for backward compatibility. Added version 2 of the MultiscaleDeformableAttention plugin - Added version 2 of the MultiscaleDeformableAttention plugin (
MultiscaleDeformableAttnPlugin_TRT), that implements the IPluginV3 interface. The legacy version (1), that implements the IPluginV2DynamicExt interface, is maintained for backward compatibility. - Added version 2 of the ModulatedDeformableConv2D plugin (
ModulatedDeformConv2d), that implements the IPluginV3 interface. The legacy version (1), that implements the IPluginV2DynamicExt interface, is maintained for backward compatibility.
- Added version 2 of the DisentangledAttention plugin (
- TensorRT 10.11 enhances support for large tensors; with most layers now capable of handling large dimensions.
Documentation
TensorRT 10.11 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.11 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.11 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.11 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.11 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.11 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.11 GA for Linux x86_64 and CUDA 12.0 to 12.9 TAR Package
- TensorRT 10.11 GA for Ubuntu 20.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.11 GA for Ubuntu 22.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.11 GA for Ubuntu 24.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.11 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.11 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.9 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.11 GA for Windows 10, 11, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.11 GA for Windows 10, 11, Server 2022 and CUDA 12.0 to 12.9 ZIP Package
TensorRT 10.11 GA for ARM SBSA
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.10 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.10 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.10 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.10 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.10 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.10 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.10 GA for Linux x86_64 and CUDA 12.0 to 12.9 TAR Package
- TensorRT 10.10 GA for Ubuntu 20.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.10 GA for Ubuntu 22.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.10 GA for Ubuntu 24.04 and CUDA 12.0 to 12.9 DEB local repo Package
- TensorRT 10.10 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.9 RPM local repo Package
- TensorRT 10.10 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.9 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.10 GA for Windows 10, 11, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.10 GA for Windows 10, 11, Server 2022 and CUDA 12.0 to 12.9 ZIP Package
TensorRT 10.10 GA for ARM SBSA
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.9 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.9 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.9 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.9 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.9 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.9 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.9 GA for Linux x86_64 and CUDA 12.0 to 12.8 TAR Package
- TensorRT 10.9 GA for Ubuntu 20.04 and CUDA 12.0 to 12.8 DEB local repo Package
- TensorRT 10.9 GA for Ubuntu 22.04 and CUDA 12.0 to 12.8 DEB local repo Package
- TensorRT 10.9 GA for Ubuntu 24.04 and CUDA 12.0 to 12.8 DEB local repo Package
- TensorRT 10.9 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.8 RPM local repo Package
- TensorRT 10.9 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.8 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.9 GA for Windows 10, 11, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.9 GA for Windows 10, 11, Server 2022 and CUDA 12.0 to 12.8 ZIP Package
TensorRT 10.9 GA for ARM SBSA
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.8 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.8 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.8 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.8 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.8 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.8 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.8 GA for Linux x86_64 and CUDA 12.0 to 12.8 TAR Package
- TensorRT 10.8 GA for Ubuntu 20.04 and CUDA 12.0 to 12.8 DEB local repo Package
- TensorRT 10.8 GA for Ubuntu 22.04 and CUDA 12.0 to 12.8 DEB local repo Package
- TensorRT 10.8 GA for Ubuntu 24.04 and CUDA 12.0 to 12.8 DEB local repo Package
- TensorRT 10.8 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.8 RPM local repo Package
- TensorRT 10.8 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.8 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.8 GA for Windows 10, 11, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.8 GA for Windows 10, 11, Server 2022 and CUDA 12.0 to 12.8 ZIP Package
TensorRT 10.8 GA for ARM SBSA
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.7 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.7 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.7 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.7 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.7 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.7 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.7 GA for Linux x86_64 and CUDA 12.0 to 12.6 TAR Package
- TensorRT 10.7 GA for Ubuntu 20.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.7 GA for Ubuntu 22.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.7 GA for Ubuntu 24.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.7 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.6 RPM local repo Package
- TensorRT 10.7 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.6 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.7 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.7 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 12.0 to 12.6 ZIP Package
TensorRT 10.7 GA for ARM SBSA
Debian and TAR Install Packages for Linux
- TensorRT 10.7 GA for Ubuntu 24.04 and CUDA 12.6 TAR Package
- TensorRT 10.7 GA for Ubuntu 24.04 and CUDA 12.6 DEB local repo Package
- TensorRT 10.7 GA for Ubuntu 24.04 and CUDA 12.6 DEB cross local repo Package
TensorRT 10.7 GA for JetPack
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.6 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.6 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.6 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.6 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.6 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.6 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.6 GA for Linux x86_64 and CUDA 12.0 to 12.6 TAR Package
- TensorRT 10.6 GA for Ubuntu 20.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.6 GA for Ubuntu 22.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.6 GA for Ubuntu 24.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.6 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.6 RPM local repo Package
- TensorRT 10.6 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.6 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.6 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.6 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 12.0 to 12.6 ZIP Package
TensorRT 10.6 GA for ARM SBSA
Debian and TAR Install Packages for Linux
- TensorRT 10.6 GA for Ubuntu 24.04 and CUDA 12.6 TAR Package
- TensorRT 10.6 GA for Ubuntu 24.04 and CUDA 12.6 DEB local repo Package
- TensorRT 10.6 GA for Ubuntu 24.04 and CUDA 12.6 DEB cross local repo Package
TensorRT 10.6 GA for JetPack
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.5 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.5 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.5 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.5 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.5 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.5 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.5 GA for Linux x86_64 and CUDA 12.0 to 12.6 TAR Package
- TensorRT 10.5 GA for Ubuntu 20.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.5 GA for Ubuntu 22.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.5 GA for Ubuntu 24.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.5 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.6 RPM local repo Package
- TensorRT 10.5 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.6 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.5 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.5 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 12.0 to 12.6 ZIP Package
TensorRT 10.5 GA for ARM SBSA
Debian and TAR Install Packages for Linux
- TensorRT 10.5 GA for Ubuntu 24.04 and CUDA 12.6 TAR Package
- TensorRT 10.5 GA for Ubuntu 24.04 and CUDA 12.6 DEB local repo Package
- TensorRT 10.5 GA for Ubuntu 24.04 and CUDA 12.6 DEB cross local repo Package
TensorRT 10.5 GA for JetPack
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.4 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.4 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.4 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.4 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.4 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.4 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.4 GA for Linux x86_64 and CUDA 12.0 to 12.6 TAR Package
- TensorRT 10.4 GA for Ubuntu 20.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.4 GA for Ubuntu 22.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.4 GA for Ubuntu 24.04 and CUDA 12.0 to 12.6 DEB local repo Package
- TensorRT 10.4 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.6 RPM local repo Package
- TensorRT 10.4 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.6 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.4 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.4 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 12.0 to 12.6 ZIP Package
TensorRT 10.4 GA for ARM SBSA
Debian and TAR Install Packages for Linux
- TensorRT 10.4 GA for Ubuntu 24.04 and CUDA 12.6 TAR Package
- TensorRT 10.4 GA for Ubuntu 24.04 and CUDA 12.6 DEB local repo Package
- TensorRT 10.4 GA for Ubuntu 24.04 and CUDA 12.6 DEB cross local repo Package
TensorRT 10.4 GA for JetPack
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.3 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.3 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.3 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.3 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.3 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.3 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.3 GA for Linux x86_64 and CUDA 12.0 to 12.5 TAR Package
- TensorRT 10.3 GA for Ubuntu 20.04 and CUDA 12.0 to 12.5 DEB local repo Package
- TensorRT 10.3 GA for Ubuntu 22.04 and CUDA 12.0 to 12.5 DEB local repo Package
- TensorRT 10.3 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.5 RPM local repo Package
- TensorRT 10.3 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.5 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.3 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.3 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 12.0 to 12.5 ZIP Package
TensorRT 10.3 GA for ARM SBSA
Debian and TAR Install Packages for Linux
- TensorRT 10.3 GA for Ubuntu 22.04 and CUDA 12.5 TAR Package
- TensorRT 10.3 GA for Ubuntu 22.04 and CUDA 12.5 DEB local repo Package
- TensorRT 10.3 GA for Ubuntu 22.04 and CUDA 12.5 DEB cross local repo Package
TensorRT 10.3 GA for JetPack
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.2 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.2 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.2 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.2 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.2 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.2 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.2 GA for Linux x86_64 and CUDA 12.0 to 12.5 TAR Package
- TensorRT 10.2 GA for Ubuntu 20.04 and CUDA 12.0 to 12.5 DEB local repo Package
- TensorRT 10.2 GA for Ubuntu 22.04 and CUDA 12.0 to 12.5 DEB local repo Package
- TensorRT 10.2 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.5 RPM local repo Package
- TensorRT 10.2 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.5 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.2 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.2 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 12.0 to 12.5 ZIP Package
TensorRT 10.2 GA for ARM SBSA
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.1 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.1 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.1 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.1 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.1 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.1 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.1 GA for Linux x86_64 and CUDA 12.0 to 12.4 TAR Package
- TensorRT 10.1 GA for Ubuntu 20.04 and CUDA 12.0 to 12.4 DEB local repo Package
- TensorRT 10.1 GA for Ubuntu 22.04 and CUDA 12.0 to 12.4 DEB local repo Package
- TensorRT 10.1 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.4 RPM local repo Package
- TensorRT 10.1 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.4 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.1 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.1 GA for Windows 10, 11, Server 2019, Server 2022 and CUDA 12.0 to 12.4 ZIP Package
TensorRT 10.1 GA for ARM SBSA
Debian and TAR Install Packages for Linux
- TensorRT 10.1 GA for Ubuntu 22.04 and CUDA 12.4 TAR Package
- TensorRT 10.1 GA for Ubuntu 22.04 and CUDA 12.4 DEB local repo Package
TensorRT 10.1 GA for JetPack
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.0 GA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.0 GA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.0 GA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.0 GA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.0 GA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.0 GA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.0 GA for Linux x86_64 and CUDA 12.0 to 12.4 TAR Package
- TensorRT 10.0 GA for Ubuntu 20.04 and CUDA 12.0 to 12.4 DEB local repo Package
- TensorRT 10.0 GA for Ubuntu 22.04 and CUDA 12.0 to 12.4 DEB local repo Package
- TensorRT 10.0 GA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.4 RPM local repo Package
- TensorRT 10.0 GA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.4 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.0 GA for Windows 10 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.0 GA for Windows 10 and CUDA 12.0 to 12.4 ZIP Package
TensorRT 10.0 GA for ARM SBSA
Debian and TAR Install Packages for Linux
- TensorRT 10.0 GA for Ubuntu 22.04 and CUDA 12.4 TAR Package
- TensorRT 10.0 GA for Ubuntu 22.04 and CUDA 12.4 DEB local repo Package
TensorRT 10.0 GA for JetPack
Debian and TAR Install Packages for Linux
Please download the version compatible with your development environment.
Documentation
TensorRT 10.0 EA for x86_64 Architecture
Debian, RPM, and TAR Install Packages for Linux
- TensorRT 10.0 EA for Linux x86_64 and CUDA 11.0 to 11.8 TAR Package
- TensorRT 10.0 EA for Ubuntu 20.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.0 EA for Ubuntu 22.04 and CUDA 11.0 to 11.8 DEB local repo Package
- TensorRT 10.0 EA for RedHat / Rocky Linux 8 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.0 EA for RedHat / Rocky Linux 9 and CUDA 11.0 to 11.8 RPM local repo Package
- TensorRT 10.0 EA for Linux x86_64 and CUDA 12.0 to 12.4 TAR Package
- TensorRT 10.0 EA for Ubuntu 20.04 and CUDA 12.0 to 12.4 DEB local repo Package
- TensorRT 10.0 EA for Ubuntu 22.04 and CUDA 12.0 to 12.4 DEB local repo Package
- TensorRT 10.0 EA for RedHat / Rocky Linux 8 and CUDA 12.0 to 12.4 RPM local repo Package
- TensorRT 10.0 EA for RedHat / Rocky Linux 9 and CUDA 12.0 to 12.4 RPM local repo Package
Zip Packages for Windows
- TensorRT 10.0 EA for Windows 10 and CUDA 11.0 to 11.8 ZIP Package
- TensorRT 10.0 EA for Windows 10 and CUDA 12.0 to 12.4 ZIP Package
TensorRT 10.0 EA for ARM SBSA
Debian and TAR Install Packages for Linux
TensorRT is also available on the following NVIDIA GPU platforms:
- NVIDIA NIM for developing AI-powered enterprise applications and deploying AI models in production
- NVIDIA GPU Cloud (NGC) TensorRT Container for cloud deployment
- NVIDIA Jetpack for Jetson Orin embedded platforms
- NVIDIA DRIVE® Install for NVIDIA DRIVE autonomous driving platform (access requires membership of the NVIDIA Drive Developer Program)
Ethical AI
NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.