OpenCV · 2026-06-08 · major
OpenCV 5.0 Ships With Built-In LLM and VLM Inference — Rewritten Graph-Based DNN Engine Pushes ONNX Coverage From ~22% to Over 80%, Native Tokenizer and KV-Cache Run Qwen 2.5, Gemma 3, PaliGemma, and GPT-Family Models Out of the Box
First major OpenCV release in a decade rewrites the deep-learning stack — graph-based DNN engine with operator fusion, 80%+ ONNX coverage, native LLM/VLM tokenizer plus KV-cache, and hardware backends across Intel IPP, Arm KleidiCV, Qualcomm FastCV, and RISC-V Vector.
The most-installed computer-vision library lands version 5.0 with a graph-based DNN engine and built-in LLM / VLM inference, timed for CVPR 2026 in Denver.
Key specs
| License | Apache-2.0 |
|---|---|
| GitHub stars | 88,404 |
| Onnx coverage | 80%+ |
| Language | C++ / Python |
| Min cpp | C++17 |
| Tag | 5.0.0 |
What is it?
OpenCV is the open-source computer-vision library that ships in roughly a million pip installs a day and powers everything from robotics pipelines to phone cameras. Version 5.0 is the first major bump since the OpenCV 3.0 era, with a rewritten DNN (deep neural network) engine and first-class LLM and VLM (vision-language model) inference. The same library that does Canny edges can now decode tokens for Qwen 2.5, Gemma 3, PaliGemma, and GPT-family architectures.
How does it work?
The new DNN engine is graph-based with operator fusion and pushes ONNX operator coverage from about 22% to over 80%, plus dynamic shapes and If/Loop control-flow subgraphs. LLM/VLM inference ships with a native tokenizer and a KV-cache for autoregressive decoding. A new hardware abstraction layer routes work through Intel IPP (IPPICV), Arm KleidiCV, Qualcomm FastCV, and RISC-V Vector backends. The C++ floor moves to C++17, the Python bindings get NumPy 2.x and new FP16, BF16, bool, and 64-bit integer types, and the legacy C API and Python 2 support are gone. The 5.0.0 tag was cut on GitHub on June 6 and the pip wheels landed June 8.
Why does it matter?
Teams that wanted classical CV plus modern LLM/VLM workloads have been gluing OpenCV to a separate inference runtime — ONNX Runtime, llama.cpp, or vendor SDKs — for years. With 5.0 the same dependency covers camera I/O, classical CV, ONNX-shaped neural nets, language and vision-language models, and edge accelerators. The release also clears a decade of API debt: C++17 baseline, NumPy 2.x, no legacy C, and a hardware layer that finally treats Arm and RISC-V as first-class.
Who is it for?
computer-vision engineers, robotics teams, edge ML developers
Try it
pip install --upgrade opencv-python