huggingface/optimum

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

90
/ 100
Verified

Supports hardware-specific backends including ONNX Runtime, OpenVINO, TensorRT-LLM, AWS Neuron, and Intel Gaudi through modular installations, enabling optimized inference across diverse accelerators. Provides unified APIs for model export, quantization, and graph optimization while maintaining compatibility with PyTorch, enabling deployment from research to production without refactoring model code.

3,325 stars and 1,613,657 monthly downloads. Used by 29 other packages. Actively maintained with 4 commits in the last 30 days. Available on PyPI.

Maintenance 16 / 25
Adoption 25 / 25
Maturity 25 / 25
Community 24 / 25

How are scores calculated?

Stars

3,325

Forks

624

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Monthly downloads

1,613,657

Commits (30d)

4

Dependencies

5

Reverse dependents

29

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/huggingface/optimum"

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