Welcome to OpenVINO™, an open-source software toolkit for optimizing and deploying deep learning models.

• Inference Optimization: Boost deep learning performance in computer vision, automatic speech recognition, generative AI, natural language processing with large and small language models, and many other common tasks.
• Flexible Model Support: Use models trained with popular frameworks such as TensorFlow, PyTorch, ONNX, Keras, and PaddlePaddle. Convert and deploy models without original frameworks.
• Broad Platform Compatibility: Reduce resource demands and efficiently deploy on a range of platforms from edge to cloud. OpenVINO™ supports inference on CPU (x86, ARM), GPU (OpenCL capable, integrated and discrete) and AI accelerators (Intel NPU).
• Community and Ecosystem: Join an active community contributing to the enhancement of deep learning performance across various domains.

Check out the OpenVINO Cheat Sheet for a quick reference.

Get your preferred distribution of OpenVINO or use this command for quick installation:

pip install -U openvino

Check system requirements and supported devices for detailed information.

OpenVINO Quickstart example will walk you through the basics of deploying your first model.

Learn how to optimize and deploy popular models with the OpenVINO Notebooks📚:

• Create an LLM-powered Chatbot using OpenVINO
• YOLOv11 Optimization
• Text-to-Image Generation
• Multimodal assistant with LLaVa and OpenVINO
• Automatic speech recognition using Whisper and OpenVINO

Here are easy-to-follow code examples demonstrating how to run PyTorch and TensorFlow model inference using OpenVINO:

PyTorch Model

import openvino as ov
import torch
import torchvision

# load PyTorch model into memory
model = torch.hub.load("pytorch/vision", "shufflenet_v2_x1_0", weights="DEFAULT")

# convert the model into OpenVINO model
example = torch.randn(1, 3, 224, 224)
ov_model = ov.convert_model(model, example_input=(example,))

# compile the model for CPU device
core = ov.Core()
compiled_model = core.compile_model(ov_model, 'CPU')

# infer the model on random data
output = compiled_model({0: example.numpy()})

TensorFlow Model

import numpy as np
import openvino as ov
import tensorflow as tf

# load TensorFlow model into memory
model = tf.keras.applications.MobileNetV2(weights='imagenet')

# convert the model into OpenVINO model
ov_model = ov.convert_model(model)

# compile the model for CPU device
core = ov.Core()
compiled_model = core.compile_model(ov_model, 'CPU')

# infer the model on random data
data = np.random.rand(1, 224, 224, 3)
output = compiled_model({0: data})

OpenVINO also supports CPU, GPU, and NPU devices and works with models in TensorFlow, PyTorch, ONNX, TensorFlow Lite, PaddlePaddle model formats. With OpenVINO you can do automatic performance enhancements at runtime customized to your hardware (preserving model accuracy), including: asynchronous execution, batch processing, tensor fusion, load balancing, dynamic inference parallelism, automatic BF16 conversion, and more.

• 🤗Optimum Intel - a simple interface to optimize Transformers and Diffusers models.
• Neural Network Compression Framework (NNCF) - advanced model optimization techniques including quantization, filter pruning, binarization, and sparsity.
• GenAI Repository and OpenVINO Tokenizers - resources and tools for developing and optimizing Generative AI applications.
• OpenVINO™ Model Server (OVMS) - a scalable, high-performance solution for serving models optimized for Intel architectures.
• Intel® Geti™ - an interactive video and image annotation tool for computer vision use cases.

Check out the Awesome OpenVINO repository to discover a collection of community-made AI projects based on OpenVINO!

User documentation contains detailed information about OpenVINO and guides you from installation through optimizing and deploying models for your AI applications.

Developer documentation focuses on how OpenVINO components work and describes building and contributing processes.

Check out Contribution Guidelines for more details. Read the Good First Issues section, if you're looking for a place to start contributing. We welcome contributions of all kinds!

You can ask questions and get support on:

• GitHub Issues.
• OpenVINO channels on the Intel DevHub Discord server.
• The openvino tag on Stack Overflow*.

• Product Page
• Release Notes
• OpenVINO Blog
• OpenVINO™ toolkit on Medium

OpenVINO™ collects software performance and usage data for the purpose of improving OpenVINO™ tools. This data is collected directly by OpenVINO™ or through the use of Google Analytics 4. You can opt-out at any time by running the command:

opt_in_out --opt_out

More Information is available at OpenVINO™ Telemetry.

OpenVINO™ Toolkit is licensed under Apache License Version 2.0. By contributing to the project, you agree to the license and copyright terms therein and release your contribution under these terms.

* Other names and brands may be claimed as the property of others.