qbxlvnf11/convert-pytorch-onnx-tensorrt

Converting weights of Pytorch models to ONNX & TensorRT engines

41
/ 100
Emerging

This tool helps deep learning engineers and MLOps professionals accelerate the performance of their PyTorch models for deployment. It takes a trained PyTorch model and converts it into optimized ONNX and TensorRT engine formats, resulting in faster inference. The end product is a highly efficient deep learning model ready for production environments.

No commits in the last 6 months.

Use this if you need to significantly speed up the inference time of your PyTorch deep learning models on NVIDIA GPUs.

Not ideal if you are working with non-PyTorch models or do not require high-performance inference on NVIDIA hardware.

deep-learning-deployment model-optimization AI-inference MLOps GPU-acceleration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

50

Forks

11

Language

Python

License

MIT

Last pushed

Mar 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/qbxlvnf11/convert-pytorch-onnx-tensorrt"

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