openvinotoolkit/openvino
Open-source AI inference optimization and deployment toolkit
- Daily
- #13
- Today
- +24
- Stars
- 11.4k
- Daily peak
- #13
- Days on chart
- 2
What it is
OpenVINO™ is an open-source toolkit for optimizing and deploying deep learning inference. It converts models from frameworks like PyTorch, TensorFlow, and ONNX so they can be deployed without the original frameworks.
Who it is for
AI developers and engineers looking to deploy computer vision, speech recognition, and generative AI models efficiently across CPUs, GPUs, and NPUs.
Why it is trending
Started in 2018, the project has accumulated 11,214 stars, gained 18 stars today, and recently released version 2026.4.1. It stands out for its broad integration across AI ecosystem tools such as Hugging Face Optimum Intel, vLLM, and LangChain.
Main features
- Convert and run models from PyTorch, TensorFlow, ONNX, Keras, and JAX/Flax
- Inference across x86/ARM CPUs, Intel integrated and discrete GPUs, and Intel NPUs
- APIs in C++, Python, C, and NodeJS, plus a dedicated GenAI API
- Integrations with NNCF quantization, OVMS serving, vLLM, LangChain, and LlamaIndex
Summarized on November 18, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary