Infrastructure / Core ML frameworks & libraries

OpenVINO

OpenVINO is an open source toolkit for optimizing and deploying AI inference across computer vision, speech, NLP, and generative AI. It converts models from PyTorch, TensorFlow, and ONNX and deploys across CPUs (x86, ARM), Intel integrated/discrete GPUs, and Intel NPUs, with a GenAI API for LLM pipelines. It is developed by Intel and integrates with Hugging Face Optimum Intel and vLLM.

Verified live 2026-06-22 via primary sources. Apache-2.0 license body confirmed; full source public.

Openness

5 high confidence

5.0

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

Apache-2.0 license body confirmed; full source public.

https://github.com/openvinotoolkit/openvino/blob/master/LICENSE recorded 2026-06-22
Apache License Version 2.0 full text

Adoption

3 high confidence

3.0

PyPI last_month downloads ~1.38M.

https://pypistats.org/api/packages/openvino/recent recorded 2026-06-22
last_month=1,379,327 downloads

Capability

4 high confidence

4.0

Broad inference runtime with model conversion and GenAI API, primarily Intel-hardware oriented.

https://github.com/openvinotoolkit/openvino recorded 2026-06-22
README: optimize/deploy inference, convert from PyTorch/TF/ONNX, CPU/GPU/NPU targets

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