cyrusbehr/tensorrt-cpp-api

TensorRT C++ API Tutorial

/ 100

Emerging

This project helps machine learning engineers and researchers accelerate the performance of their GPU-based machine learning models. You can take an existing ONNX model and generate a highly optimized TensorRT engine file for faster inference. This allows you to deploy models like YOLOv8 or ArcFace on NVIDIA GPUs with significantly reduced inference times, transforming ONNX input into optimized GPU model output.

793 stars. No commits in the last 6 months.

Use this if you need to deploy your computer vision models for high-performance, real-time inference on NVIDIA GPUs using C++.

Not ideal if you are working with dynamic input shapes, require Windows support, or are not comfortable with C++ development and GPU-specific optimizations.

GPU-inference computer-vision real-time-AI model-deployment deep-learning-optimization

Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 10 / 25

Maturity 16 / 25

Community 20 / 25

How are scores calculated?

Stars

793

Forks

103

Language

C++

License

MIT

Higher-rated alternatives

microsoft/onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

onnx/onnx

Open standard for machine learning interoperability

PINTO0309/onnx2tf

Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...

NVIDIA/TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...

onnx/onnxmltools

ONNXMLTools enables conversion of models to ONNX

Explore ML Frameworks

All categories Trending ML Framework directory Insights