laugh12321/TensorRT-YOLO

Health v2 · maintenance only

Adoption not part of the score

1880 stars · 194 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A C++/Python deployment toolkit for running YOLO-family models (YOLOv3 through YOLO26) on NVIDIA GPUs using TensorRT, with custom plugins, CUDA kernels, and CUDA Graphs for accelerated inference. It supports object detection, instance segmentation, image classification, pose estimation, rotated object detection, and video analysis out of the box.

Use cases

• deploy yolo models on nvidia gpu with tensorrt
• run yolov8 inference in c++
• convert ultralytics yolo model to tensorrt engine
• fast object detection inference with cuda graphs
• instance segmentation deployment on jetson
• pose estimation inference in python
• rotated object detection (obb) deployment
• video stream analysis with yolo

When to choose

• you need maximum YOLO inference performance on NVIDIA hardware via TensorRT
• you want C++ and Python APIs with minimal third-party dependencies
• you need support for many YOLO variants and tasks (detect, segment, classify, pose, OBB) out of the box

When to avoid

• you are not targeting NVIDIA GPUs or don't use TensorRT
• you need a non-YOLO model architecture
• you require a permissive license (project is GPL-3.0)

Facets

library · maturity active

machine-learning computer-vision image-processing gpu-computing sdk computer-vision deep-learning machine-learning gpu-computing image-processing cpp python tensorrt yolo object-detection instance-segmentation pose-estimation cuda nvidia inference-deployment ultralytics obb linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="laugh12321/TensorRT-YOLO")