ONNX Runtime
The portable inference engine that runs one ONNX model from server to browser.
ONNX Runtime, built by Microsoft, loads a model in the ONNX format exported from PyTorch, TensorFlow or scikit-learn and runs it through interchangeable execution providers: CPU, CUDA, TensorRT, OpenVINO, DirectML, CoreML, NNAPI, or WebAssembly and WebGPU in the browser. The graph is optimized at load time (constant folding, operator fusion) and can be quantized to INT8, with APIs for Python, C++, C#, Java and JavaScript. It's our choice when the same model has to run on heterogeneous targets without being recompiled for each one.
What ONNX Runtime brings to your project.
Typical use cases: Inference on CPU servers, Windows or macOS desktop apps, and models embedded in the browser.
- 01
CPU, CUDA, TensorRT, OpenVINO, DirectML and CoreML execution providers: one model, many accelerators.
- 02
Load-time graph optimizations plus static or dynamic INT8 quantization.
- 03
onnxruntime-web: in-browser inference through WebAssembly or WebGPU, no backend needed.
- 04
MIT license, Python, C++, C#, Java and JavaScript APIs, GenAI extension for LLMs.
Entrust your project
to our experts.
Entrust your project to our
experts.
Entrust your project
to our experts.
Our experts build your project, delivering superior technical and functional quality within shorter timeframes.
They trust us.
They trust
us.
Startups, mid-caps, large enterprises, public sector: Kosmos supports organisations of every size in building their web, mobile and AI applications.
They talk about us.
Explore the mentions and analyses that spotlight our work and our innovations across the business and tech press.
A project with ONNX Runtime?
Describe your project. Our team replies within 24 hours with free technical scoping, along with a clear estimate of costs and timelines. No commitment.
- Reply within 24 hours from a project manager
or engineer.Reply within 24 hours from a project manager or engineer. - Technical scoping and quote, with no fees.
- No commitment, your data stays
confidential.No commitment, your data stays confidential.
Monday to Saturday · 9am to 6:30pm
hello@kosmos-digital.com
Paris · Lyon · Marseille · Nice · Geneva
Your company may qualify for a tax credit equal to 20% of the costs linked to developing its solution.
Free scoping & estimate in less than 24h
Describe your project and we'll get back to you with a costed estimate and a roadmap.