mindspore-lab/mindnlp

MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless compatibility and acceleration.

64
/ 100
Established

This project helps AI developers and researchers efficiently run a vast array of pre-trained AI models, including large language models and image generation models, on MindSpore with hardware acceleration. It takes existing HuggingFace model code and outputs accelerated model execution on various hardware like Ascend NPUs or NVIDIA GPUs, without requiring code changes. This is primarily used by machine learning engineers, data scientists, and AI researchers working with MindSpore.

913 stars. Actively maintained with 1 commit in the last 30 days.

Use this if you are a machine learning engineer or researcher looking to deploy and accelerate HuggingFace models on MindSpore, especially if you need native support for Ascend NPUs.

Not ideal if you are exclusively working with PyTorch or TensorFlow ecosystems and do not use MindSpore for model deployment or acceleration.

AI-model-deployment natural-language-processing computer-vision deep-learning-acceleration large-language-models
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

913

Forks

267

Language

Python

License

Apache-2.0

Last pushed

Mar 08, 2026

Commits (30d)

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mindspore-lab/mindnlp"

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