Infrastructure / Core ML frameworks & libraries

Optimum

Optimum is an extension of Transformers, Diffusers, TIMM, and Sentence-Transformers that provides tools to optimize training and inference on targeted hardware. It supports accelerators and runtimes including ONNX Runtime, OpenVINO, Intel Gaudi, AWS Trainium/Inferentia, and NVIDIA TensorRT-LLM, and handles model export and quantization. It is maintained by Hugging Face.

Verified live 2026-06-22 via primary sources. LICENSE body is verbatim Apache License 2.0; full source public.

Openness

5 high confidence

5.0

license: Apache-2.0(OSI)
source: public
core-gated: ungated

LICENSE body is verbatim Apache License 2.0; full source public.

https://github.com/huggingface/optimum/blob/main/LICENSE recorded 2026-06-22
LICENSE file is the verbatim Apache License Version 2.0

Adoption

3 high confidence

3.0

PyPI last-month downloads of 1,759,764 fall in the 500k-5M range.

https://pypistats.org/api/packages/optimum/recent recorded 2026-06-22
last_month = 1,759,764 PyPI downloads

Capability

4 high confidence

4.0

Broad multi-backend optimization layer, though dependent on the core Transformers stack.

https://github.com/huggingface/optimum recorded 2026-06-22
README lists ONNX Runtime, OpenVINO, Gaudi, Trainium/Inferentia, TensorRT-LLM support

Unchanged since 2026-07-30 (last edited, not re-checked)