laugh12321/TensorRT-YOLO

🚀 Easier & Faster YOLO Deployment Toolkit for NVIDIA 🛠️

66
/ 100
Established

This project helps operations engineers and MLOps professionals deploy object detection, segmentation, and pose estimation models (YOLO series) onto NVIDIA hardware. It takes trained YOLO models (after converting them to a TensorRT engine using a separate tool) and outputs faster, more efficient inferences for tasks like identifying objects in images or tracking poses in videos. This is designed for those who need to get their computer vision models running quickly and powerfully in real-world applications.

1,730 stars. Actively maintained with 6 commits in the last 30 days.

Use this if you need to significantly speed up the inference performance of your YOLO-based computer vision models on NVIDIA GPUs for various tasks like object detection or pose estimation.

Not ideal if you are still in the model training phase or if you are not working with NVIDIA hardware for deployment.

computer-vision object-detection image-segmentation pose-estimation MLOps
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

1,730

Forks

182

Language

C++

License

GPL-3.0

Last pushed

Mar 16, 2026

Commits (30d)

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/laugh12321/TensorRT-YOLO"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.