Ascend/pytorch

Ascend PyTorch adapter (torch_npu). Mirror of https://gitcode.com/Ascend/pytorch

53
/ 100
Established

This project provides an extension for PyTorch, called torch_npu, to enable your PyTorch-based AI models and workflows to run on Ascend NPU hardware. It takes your existing PyTorch code and allows it to leverage the high-performance computing capabilities of Ascend AI Processors. AI/ML engineers and researchers who are developing and deploying deep learning models will find this useful for accelerating their computational tasks.

493 stars.

Use this if you are a machine learning engineer or researcher using PyTorch and want to significantly speed up your deep learning model training and inference by utilizing Ascend AI Processors.

Not ideal if you are not working with PyTorch, do not have access to Ascend AI Processors, or your application does not require high-performance AI acceleration.

deep-learning AI-acceleration model-training neural-networks high-performance-computing
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

493

Forks

48

Language

Python

License

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

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

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