yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
- 58k
- Python
- AGPL-3.0
- 4 d ago
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Repo NVIDIA/TensorRT, read from GitHub 4 h ago. NVIDIA has not joined Take My Repo.
NVIDIA/TensorRT is a public repo on GitHub by NVIDIA. NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT. It declares the Apache-2.0 license on GitHub. It is written mainly in C++, has 13,471 stars and last changed on 2026-11-18. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from GitHub on 2026-11-20.
In the maintainer's words. Shown from GitHub; Take My Repo does not keep a copy.
TensorRT 11.X is now released with powerful new capabilities designed to accelerate your AI inference workflows. With this major version bump, TensorRT's API has been streamlined and a few legacy features from 10.X have been removed.
Below provides migration guides for the following features:
This repository contains the Open Source Software (OSS) components of NVIDIA TensorRT. It includes the sources for TensorRT plugins and ONNX parser, as well as sample applications demonstrating usage and capabilities of the TensorRT platform. These open source software components are a subset of the TensorRT General Availability (GA) release with some extensions and bug-fixes.
Need enterprise support? NVIDIA global support is available for TensorRT with the NVIDIA AI Enterprise software suite. Check out NVIDIA LaunchPad for free access to a set of hands-on labs with TensorRT hosted on NVIDIA infrastructure.
Join the TensorRT and Triton community and stay current on the latest product updates, bug fixes, content, best practices, and more.
Various skills related to TensorRT usage and benchmarking are available here. For installation, refer to the instructions of your preferred coding agent.
We provide the TensorRT Python package for an easy installation.
To install:
pip install tensorrt
You can skip the Build section to enjoy TensorRT with Python.
To build the TensorRT-OSS components, you will first need the following software packages.
TensorRT GA build
System Packages
Optional Packages
NCCL >= v2.19, < v3.0 — only when building with multi-device support (-DTRT_BUILD_ENABLE_MULTIDEVICE=ON) for the sampleDistCollective sample.
Containerized build
PyPI packages (for demo applications/tests)
Code formatting tools (for contributors)
NOTE: onnx-tensorrt, cub, and protobuf packages are downloaded along with TensorRT OSS, and not required to be installed.
git clone -b main https://github.com/nvidia/TensorRT TensorRT
cd TensorRT
git submodule update --init --recursiveIf using the TensorRT OSS build container, TensorRT libraries are preinstalled under /usr/lib/x86_64-linux-gnu and you may skip this step.
Else download and extract the TensorRT GA build from NVIDIA Developer Zone with the direct links below:
Example: Ubuntu 22.04 on x86-64 with cuda-13.5
cd ~/Downloads tar --zstd -xvf TensorRT-Enterprise-11.5.0.63-Linux-x86_64-cuda-13.5-Release-external.tar.zst export TRT_LIBPATH=`pwd`/TensorRT-11.5.0.63/lib
Example: Windows on x86-64 with cuda-12.9
Expand-Archive -Path TensorRT-Enterprise-11.5.0.63-Windows-amd64-cuda-12.9-Release-external.zip $env:TRT_LIBPATH="$pwd\TensorRT-11.5.0.63\lib"
For Linux platforms, we recommend that you generate a docker container for building TensorRT OSS as described below. For native builds, please install the prerequisite System Packages.
Example: Ubuntu 24.04 on x86-64 with cuda-13.5 (default)
./docker/build.sh --file docker/ubuntu-24.04.Dockerfile --tag tensorrt-ubuntu24.04-cuda13.5
Example: Rockylinux8 on x86-64 with cuda-13.5
./docker/build.sh --file docker/rockylinux8.Dockerfile --tag tensorrt-rockylinux8-cuda13.5
Example: Ubuntu 24.04 cross-compile for Jetson (aarch64) with cuda-13.5 (JetPack SDK)
./docker/build.sh --file docker/ubuntu-cross-aarch64.Dockerfile --tag tensorrt-jetpack-cuda13.5
Example: Ubuntu 24.04 on aarch64 with cuda-13.5
./docker/build.sh --file docker/ubuntu-24.04-aarch64.Dockerfile --tag tensorrt-aarch64-ubuntu24.04-cuda13.5
Example: Ubuntu 24.04 build container
./docker/launch.sh --tag tensorrt-ubuntu24.04-cuda13.5 --gpus all
NOTE:
1. Use the--tagcorresponding to build container generated in Step 1.
2. NVIDIA Container Toolkit is required for GPU access (running TensorRT applications) inside the build container.
3.sudopassword for Ubuntu build containers is 'nvidia'.
4. Specify port number using--jupyter <port>for launching Jupyter notebooks.
5. Write permission to this folder is required as this folder will be mounted inside the docker container for uid:gid of 1000:1000.
Generate Makefiles and build
Example: Linux (x86-64) build with default cuda-13.5
cd $TRT_OSSPATH mkdir -p build && cd build cmake .. -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/out make -j$(nproc)
Example: Linux (aarch64) build with default cuda-13.5
cd $TRT_OSSPATH mkdir -p build && cd build cmake .. -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64-native.toolchain make -j$(nproc)
Example: Native build on Jetson Thor (aarch64) with cuda-13.5
cd $TRT_OSSPATH mkdir -p build && cd build cmake .. -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/out CC=/usr/bin/gcc make -j$(nproc)
NOTE: C compiler must be explicitly specified via CC= for native aarch64 builds of protobuf.
Example: Ubuntu 24.04 Cross-Compile for Jetson Thor (aarch64) with cuda-13.5 (JetPack)
cd $TRT_OSSPATH mkdir -p build && cd build cmake .. -DCMAKE_PREFIX_PATH=$TRT_ROOT -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64_cross.toolchain make -j$(nproc)
Example: Ubuntu 24.04 Cross-Compile for DriveOS (aarch64) with cuda-13.5
cd $TRT_OSSPATH mkdir -p build && cd build cmake .. -DTRT_BUILD_PRODUCT=automotive -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64_cross.toolchain make -j$(nproc)
Example: Native builds on Windows (x86) with cuda-13.5
cd $TRT_OSSPATH New-Item -ItemType Directory -Path build cd build cmake .. -DCMAKE_PREFIX_PATH="$env:TRT_ROOT" ` -DCMAKE_RUNTIME_OUTPUT_DIRECTORY="$pwd\\out" ` -DCMAKE_LIBRARY_OUTPUT_DIRECTORY="$pwd\\out" ` -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY="$pwd\\out" msbuild TensorRT.sln /property:Configuration=Release -m:$env:NUMBER_OF_PROCESSORS
NOTE: The default CUDA version used by CMake is 13.5. To override this, for example to 12.9, append
-DCUDA_VERSION=12.9to the cmake command.
Required CMake build arguments are:
CMAKE_PREFIX_PATH: Path to the TensorRT package root containing the product CMake config.Optional CMake build arguments:
CMAKE_RUNTIME_OUTPUT_DIRECTORY, CMAKE_LIBRARY_OUTPUT_DIRECTORY, and CMAKE_ARCHIVE_OUTPUT_DIRECTORY: Native CMake output directories for executables, shared libraries, and archives. Set all three to the same path to collect generated build artifacts in one directory.CMAKE_BUILD_TYPE: Specify if binaries generated are for release or debug (contain debug symbols). Values consists of [Release] | DebugCUDA_VERSION: The version of CUDA to target, for example [12.9.9].CUDNN_VERSION: The version of cuDNN to target, for example [8.9].PROTOBUF_VERSION: The version of Protobuf to use, for example [3.20.1]. Note: Changing this will not configure CMake to use a system version of Protobuf, it will configure CMake to download and try building that version.CMAKE_TOOLCHAIN_FILE: The path to a toolchain file for cross compilation.BUILD_PARSERS: Specify if the parsers should be built, for example [ON] | OFF. If turned OFF, CMake uses the parser target imported from the TensorRT package config.BUILD_PLUGINS: Specify if the plugins should be built, for example [ON] | OFF. If turned OFF, CMake uses the plugin targets imported from the TensorRT package config.BUILD_SAMPLES: Specify if the samples should be built, for example [ON] | OFF.BUILD_SAFE_SAMPLES: Specify if safety samples should be built, for example [ON] | OFF.TRT_SAFETY_INFERENCE_ONLY: Specify if only build the safety inference components, for example [ON] | OFF. If turned ON, all other components will be turned OFF except BUILD_SAFE_SAMPLES.TRT_BUILD_PRODUCT: Select the TensorRT product package to import: enterprise, automotive, or safe_inference. If omitted, the build will infer the product based on the values of BUILD_SAFE_SAMPLES and TRT_SAFETY_INFERENCE_ONLY.TRT_BUILD_ENABLE_MULTIDEVICE: Enable the multi-device sample (sampleDistCollective). Use -DTRT_BUILD_ENABLE_MULTIDEVICE=ON to build it; requires NCCL >= v2.19, < v3.0.TRT_BUILD_TESTING : Build gTests for samples. Requires gtest if available; otherwise fetches googletest at configure time.Generate Makefiles and build
Example: Cross-Compile for DOS7 Linux (aarch64)
cd $TRT_OSSPATH mkdir -p build && cd build cmake .. -DBUILD_SAMPLES=ON -DBUILD_PLUGINS=OFF -DBUILD_PARSERS=OFF \ -DTRT_BUILD_PRODUCT=automotive \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64_cross.toolchain make -j$(nproc)
Example: Cross-Compile for DOS6.5 Linux (aarch64)
cd $TRT_OSSPATH mkdir -p build && cd build cmake .. -DBUILD_SAMPLES=ON -DBUILD_PLUGINS=OFF -DBUILD_PARSERS=OFF \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64_cross.toolchain \ -DCUDA_VERSION=11.4 -DCMAKE_CUDA_ARCHITECTURES=87 make -j$(nproc)
Example: Native build for DOS6.5 and DOS7 Linux (aarch64)
cd $TRT_OSSPATH mkdir -p build && cd build cmake .. -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/out \ -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64-native.toolchain \ -DBUILD_SAMPLES=ON -DBUILD_PLUGINS=OFF -DBUILD_PARSERS=OFF \ -DTRT_BUILD_PRODUCT=automotive make -j$(nproc)
Example: Cross-Compile for DOS6.5 QNX (aarch64)
cd $TRT_OSSPATH mkdir -p build && cd build export CUDA_VERSION=11.4 export CUDA=cuda-$CUDA_VERSION export CUDA_ROOT=/usr/local/cuda-safe-$CUDA_VERSION export QNX_BASE=/drive/toolchains/qnx_toolchain # Set to your QNX toolchain installation path export QNX_HOST=$QNX_BASE/host/linux/x86_64/ export QNX_TARGET=$QNX_BASE/target/qnx7/ export PATH=$PATH:$QNX_HOST/usr/bin cmake .. -DBUILD_SAMPLES=ON -DBUILD_PLUGINS=OFF -DBUILD_PARSERS=OFF -DBUILD_SAFE_SAMPLES=OFF \ -DCMAKE_CUDA_COMPILER=$CUDA_ROOT/bin/nvcc \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_qnx.toolchain \ -DCUDA_VERSION=$CUDA_VERSION -DCMAKE_CUDA_ARCHITECTURES=87 make -j$(nproc)
NOTE: Set
QNX_BASEto your QNX toolchain installation path. If your CUDA version is not the same as in the example, setCUDA_VERSION(for examples that use it in multiple places) or add-DCUDA_VERSION=<version>to the cmake command.
Example: Cross-Compile for DOS6.5 QNX Safety (aarch64)
cd $TRT_OSSPATH mkdir -p build && cd build export CUDA_VERSION=11.4 export QNX_BASE=/drive/toolchains/qnx_toolchain # Set to your QNX toolchain installation path export QNX_HOST=$QNX_BASE/host/linux/x86_64/ export QNX_TARGET=$QNX_BASE/target/qnx7/ export PATH=$PATH:$QNX_HOST/usr/bin export CUDA=cuda-$CUDA_VERSION export CUDA_ROOT=/usr/local/cuda-safe-$CUDA_VERSION cmake .. -DBUILD_SAMPLES=OFF -DBUILD_SAFE_SAMPLES=ON -DBUILD_PLUGINS=OFF -DBUILD_PARSERS=OFF \ -DTRT_SAFETY_INFERENCE_ONLY=ON \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_qnx_safe.toolchain \ -DCUDA_VERSION=$CUDA_VERSION -DCMAKE_CUDA_COMPILER=$CUDA_ROOT/bin/nvcc \ -DCMAKE_CUDA_ARCHITECTURES=87 make -j$(nproc)
NOTE: Set
QNX_BASEto your QNX toolchain installation path. If your CUDA version is not the same as in the example, setCUDA_VERSION(for examples that use it in multiple places) or add-DCUDA_VERSION=<version>to the cmake command.
Example: Cross-Compile for DOS7 QNX (aarch64)
cd $TRT_OSSPATH mkdir -p build && cd build export CUDA_VERSION=13.5 export CUDA=cuda-$CUDA_VERSION export CUDA_ROOT=/usr/local/cuda-$CUDA_VERSION export QNX_BASE=/drive/toolchains/qnx_toolchain # Set to your QNX toolchain installation path export QNX_HOST=$QNX_BASE/host/linux/x86_64/ export QNX_TARGET=$QNX_BASE/target/qnx/ export PATH=$PATH:$QNX_HOST/usr/bin cmake .. -DBUILD_SAMPLES=ON -DBUILD_PLUGINS=OFF -DBUILD_PARSERS=OFF -DBUILD_SAFE_SAMPLES=OFF \ -DTRT_BUILD_PRODUCT=automotive \ -DCMAKE_CUDA_COMPILER=$CUDA_ROOT/bin/nvcc \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_qnx.toolchain \ -DCUDA_VERSION=$CUDA_VERSION -DCMAKE_CUDA_ARCHITECTURES=110 make -j$(nproc)
NOTE: Set
QNX_BASEto your QNX toolchain installation path. If your CUDA version is not the same as in the example, setCUDA_VERSION(for examples that use it in multiple places) or add-DCUDA_VERSION=<version>to the cmake command.
Example: Cross-Compile for DOS7 QNX Safety (aarch64)
DOS7 QNX and QNX Safety use the same QNX 8 SDK through QNX_HOST and
QNX_TARGET. The QNX Safety build additionally uses SafeCUDA, the matching
TensorRT SafeInference package, and cmake_qnx_safe.toolchain. The standard
DriveOS QNX Safety build environment provides PDK_TOP; the toolchain uses
the libraries under $PDK_TOP/drive-qnx-safety/lib-target.
cd $TRT_OSSPATH mkdir -p build && cd build export CUDA_VERSION=13.5 export CUDA=cuda-$CUDA_VERSION export CUDA_ROOT=/usr/local/cuda-$CUDA_VERSION-safe export QNX_BASE=/drive/toolchains/qnx_toolchain # Set to your QNX 8 toolchain installation path export QNX_HOST=$QNX_BASE/host/linux/x86_64/ export QNX_TARGET=$QNX_BASE/target/qnx/ export PATH=$PATH:$QNX_HOST/usr/bin cmake .. -DBUILD_SAMPLES=OFF -DBUILD_SAFE_SAMPLES=ON -DBUILD_PLUGINS=OFF -DBUILD_PARSERS=OFF \ -DTRT_BUILD_PRODUCT=safe_inference \ -DTRT_SAFETY_INFERENCE_ONLY=ON -DCMAKE_BUILD_TYPE=Release \ -DCMAKE_RUNTIME_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_ARCHIVE_OUTPUT_DIRECTORY=`pwd`/bin_dynamic_cross \ -DCMAKE_PREFIX_PATH=$TRT_ROOT \ -DTensorRT-SafeInference_DIR=$TRT_ROOT/cmake \ -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_qnx_safe.toolchain \ -DCUDA_VERSION=$CUDA_VERSION -DCMAKE_CUDA_COMPILER=$CUDA_ROOT/bin/nvcc \ -DCMAKE_CUDA_ARCHITECTURES=110 make -j$(nproc)
NOTE: Set
QNX_BASEto the same QNX 8 SDK used for DOS7 QNX builds. The generated QNX Safety binaries are placed inbuild/bin_dynamic_cross.
NVIDIA/TensorRT is a public repo on GitHub by NVIDIA. NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
It declares the Apache-2.0 license on GitHub.
Its maker has not tagged a system, so it is unknown here. Its README says what it needs.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on GitHub was on 2026-11-18. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

A high-throughput and memory-efficient inference and serving engine for LLMs


The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

OpenShell is the safe, private runtime for autonomous AI agents.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
This page is also available as structured data, with the same sources and dates.
/api/v1/resources/gh/NVIDIA/TensorRTTake My Repo has not tested this on your machine. Requirements come from the project's own documentation.