shouxieai/tensorRT_Pro

Health v2 · maintenance only

Adoption not part of the score

2892 stars · 573 forks observed · 2026-08-28

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

A C++ library built on NVIDIA TensorRT that provides a high-level interface for high-performance deep learning inference, with Python bindings. It simplifies running models like YOLOv5 and YOLOX with just a few lines of code and supports fp32/fp16/int8 compilation.

Use cases

• deploy yolov5 models with tensorrt in c++
• run high-performance object detection inference on gpu
• convert pytorch models to tensorrt engines
• compile tensorrt models in fp16 or int8
• run yolo inference from python with minimal code

When to choose

• you need fast C++ TensorRT inference for detection models like YOLOv5/YOLOX
• you want a simple API instead of writing raw TensorRT code
• you need easy fp32/fp16/int8 model compilation

When to avoid

• you need inference on non-NVIDIA hardware
• you need models outside its supported set (e.g., transformers, segmentation)
• you want a framework with frequent updates and broad community support

Facets

library · maturity maintenance

deep-learning machine-learning image-processing sdk deep-learning computer-vision gpu-computing artificial-intelligence cpp python tensorrt yolov5 yolox inference object-detection nvidia model-deployment linux gpu docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="shouxieai/tensorRT_Pro")