OpenVINO

Health v2 · maintenance only

Adoption not part of the score

10740 stars · 3335 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

OpenVINO is an open-source toolkit from Intel for optimizing and deploying deep learning inference across CPU, GPU, and NPU hardware. It supports models from PyTorch, TensorFlow, ONNX, and Hugging Face, targeting computer vision, LLMs, speech, and generative AI workloads from edge to cloud.

Use cases

• run deep learning inference faster on intel cpu and gpu
• deploy llm inference on intel npu
• convert pytorch or onnx models to an optimized runtime
• run stable diffusion locally with better performance
• deploy computer vision models at the edge
• optimize transformer models for inference
• run speech recognition models with low latency

When to choose

• you deploy inference on Intel CPUs, integrated/discrete GPUs, or NPUs
• you need a framework-agnostic runtime for PyTorch, TensorFlow, or ONNX models
• you target edge devices with limited resources
• you want optimized LLM or Stable Diffusion inference without a GPU cluster

When to avoid

• you need NVIDIA CUDA-specific optimizations or TensorRT integration
• your workload is training rather than inference
• you only target non-Intel hardware where other runtimes may perform better

Facets

library · maturity stable

machine-learning deep-learning llm-inference computer-vision speech-recognition nlp stable-diffusion transformers gpu-computing sdk deep-learning machine-learning computer-vision artificial-intelligence gpu-computing developer-tools windows python cpp cross-platform embedded iot inference-optimization intel-hardware npu model-conversion onnx pytorch tensorflow edge-ai generative-ai runtime natural-language-processing linux macos gpu nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="openvinotoolkit/openvino")