intel/intel-extension-for-pytorch

A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

72
/ 100
Verified

This tool helps AI engineers and machine learning practitioners accelerate the performance of their PyTorch models, especially large language models (LLMs), on Intel CPU and GPU hardware. By taking existing PyTorch code, it applies Intel-specific optimizations to make models run faster and more efficiently. The output is a more performant model without needing significant code changes.

2,018 stars. Used by 1 other package. Actively maintained with 1 commit in the last 30 days. Available on PyPI.

Use this if you need to optimize the speed and efficiency of your PyTorch-based AI models, particularly large language models, when running them on Intel CPUs or GPUs.

Not ideal if you are starting new AI development, as most of its features are now integrated directly into PyTorch, or if you are not using Intel hardware, as active development has ceased.

AI model optimization Large Language Models (LLM) deep learning performance machine learning deployment AI inference
Maintenance 13 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 23 / 25

How are scores calculated?

Stars

2,018

Forks

314

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

1

Dependencies

3

Reverse dependents

1

Get this data via API

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

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