hidet-org/hidet

An open-source efficient deep learning framework/compiler, written in python.

55
/ 100
Established

This project helps deep learning engineers and researchers make their neural network models run faster on NVIDIA GPUs. It takes your existing PyTorch or ONNX deep learning models and transforms them into highly efficient CUDA kernels. The output is a significantly optimized model ready for deployment, reducing the computational resources and time needed for inference.

738 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are developing deep learning applications and need to accelerate the inference performance of your PyTorch or ONNX models on NVIDIA GPUs, especially for large-scale deployments or latency-sensitive scenarios.

Not ideal if you are working with deep learning models on CPUs or other GPU architectures, or if your primary focus is on model training rather than inference optimization.

deep-learning-optimization neural-network-inference GPU-acceleration ML-operations computational-efficiency
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

738

Forks

68

Language

Python

License

Apache-2.0

Last pushed

Sep 04, 2025

Commits (30d)

0

Dependencies

18

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hidet-org/hidet"

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