triple-mu/YOLOv8-TensorRT

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1812 stars · 300 forks observed · 2026-10-01

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

A library for running YOLOv8 inference accelerated with NVIDIA TensorRT, supporting detection, segmentation, pose estimation, oriented bounding boxes, and classification from both Python and C++. It handles ONNX export, TensorRT engine building, and version-compatible deployment across TensorRT 8 through 11.

Use cases

• accelerate yolov8 inference with tensorrt
• deploy object detection model on jetson
• run yolo segmentation in c++
• convert ultralytics model to tensorrt engine
• run pose estimation with gpu acceleration
• deploy yolo model with onnx and tensorrt
• high-speed object detection on nvidia gpu

When to choose

• you need maximum inference speed for YOLOv8 on NVIDIA GPUs or Jetson devices
• you want both Python and C++ deployment paths sharing the same engines
• you need multiple YOLOv8 tasks (detect, segment, pose, OBB, classify) with one toolchain
• you must support multiple TensorRT versions without code changes

When to avoid

• you are not using NVIDIA hardware, since TensorRT is NVIDIA-only
• you need a different model architecture than YOLOv8
• you want a simple CPU-only inference solution
• you need training or fine-tuning rather than inference

Facets

library · maturity active

machine-learning computer-vision image-processing gpu-computing llm-inference computer-vision deep-learning gpu-computing python cpp yolov8 tensorrt onnx object-detection instance-segmentation pose-estimation nvidia deepstream edge-deployment linux gpu jetson

Member repositories

For agents

markdown · JSON · MCP: product_card(name="triple-mu/YOLOv8-TensorRT")