ONNX Runtime is a cross-platform inference and training accelerator for machine-learning models.
ONNX Runtime is a cross-platform machine-learning accelerator, with built-in optimizations that speed up training and inferencing across existing technology stacks. It runs models from source frameworks including PyTorch, TensorFlow, and Hugging Face across Windows, Linux, macOS, iOS, Android, and the web, targeting CPU, GPU, and NPU hardware through pluggable execution providers.
The runtime is developed by Microsoft as the open-source microsoft/onnxruntime project and powers AI features across Microsoft products and services.
Microsoft Clarity
Microsoft-Decision-1
Microsoft Purview Insider Risk Management
Semantic Kernel
Microsoft Dragon Copilot
Microsoft Teams Phone
Microsoft Excel
Microsoft Clipchamp
Azure Kubernetes Service
Azure Cosmos DB
Azure HDInsight
Microsoft Q&A
Azure Digital Twins
Microsoft Teams Custom Backgrounds
Azure Quantum
Havok Physics
Microsoft Project Bonsai
Microsoft Project AirSim
AirSim
Microsoft Bookings
| Attribute | ONNX Runtime | Aviator | ExecuTorch | Hermes | TensorRT | |
|---|---|---|---|---|---|---|
| Provider | |  |  |  |  | |
| Founded | 1975 | 2019 | 2004 | 2025 | 1993 | |
| Sells To | Enterprises, Small Business | Enterprise | Consumers, Enterprise | — | Consumers, Enterprise | |
| Pricing Model | SaaS, Transactional | — | Advertising | — | Licensing, Product Sales, Subscription | |
| Ownership | Public | Private | Public | Venture-backed | Public |
Provider
Founded 1975
Sells To Enterprises, Small Business
Pricing Model SaaS, Transactional
Ownership Public
Provider
Founded 2019
Sells To Enterprise
Pricing Model —
Ownership Private
Provider
Founded 2004
Sells To Consumers, Enterprise
Pricing Model Advertising
Ownership Public
Provider
Founded 2025
Sells To —
Pricing Model —
Ownership Venture-backed
Provider
Founded 1993
Sells To Consumers, Enterprise
Pricing Model Licensing, Product Sales, Subscription
Ownership Public
Open-source inference serving platform for deploying AI models from any framework on CPUs and GPUs.
Open-source hybrid edge-cloud AI inference engine for mobile devices and wearables.
Open-source platform for collaborating on machine learning models, datasets, and applications.
Kneron's Edge AI Platform delivers on-device NPUs and full-stack software for edge inference.
Pipeshift's platform provides infrastructure for fine-tuning, inference, and orchestration of open-source AI models.
Hugging Face Hub is the leading platform for sharing, discovering, and deploying machine learning models and datasets.
Baseten Inference Stack for high performance with custom kernels, decoding, caching on optimized infra.
Cloudflare AI: serverless inference, agents, RAG, and secure runtime primitives on the global edge.
Open-source inference serving platform for deploying AI models from any framework on CPUs and GPUs.
Open-source hybrid edge-cloud AI inference engine for mobile devices and wearables.
Open-source platform for collaborating on machine learning models, datasets, and applications.
Kneron's Edge AI Platform delivers on-device NPUs and full-stack software for edge inference.
Pipeshift's platform provides infrastructure for fine-tuning, inference, and orchestration of open-source AI models.
Hugging Face Hub is the leading platform for sharing, discovering, and deploying machine learning models and datasets.
Replicate is a platform for running machine learning models via a simple cloud API, direct competitor to Cloudflare AI inference.
Baseten Inference Stack for high performance with custom kernels, decoding, caching on optimized infra.
Cloudflare AI: serverless inference, agents, RAG, and secure runtime primitives on the global edge.
MLPerf is an industry-standard suite that measures AI training and inference system performance.
Kubernetes-native GPU orchestration and workload management platform for AI training and inference clusters.