laugh12321/TensorRT-YOLO
GPU-accelerated inference toolkit for deploying YOLO models using TensorRT with CUDA optimization on NVIDIA hardware.
Velocity · 7d
+2.1
★ / day
Trend
→steady
star history
This repository provides an efficient deployment solution for YOLO series models (YOLOv5, YOLOv8, YOLO11, YOLO26) on NVIDIA devices. It uses TensorRT plugins, CUDA kernels, and CUDA graphs to accelerate model inference. The toolkit supports multiple computer vision tasks including object detection, instance segmentation, image classification, pose estimation, and rotated object detection, with both C++ and Python inference APIs.