# microsoft/onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Repository: https://github.com/microsoft/onnxruntime
Canonical: https://ross.abutalabs.com/products/onnxruntime
Homepage: https://onnxruntime.ai
Language: C++
License: MIT
License Family: permissive
Topics: deep-learning, onnx, neural-networks, machine-learning, ai-framework, hardware-acceleration, pytorch, tensorflow, scikit-learn
Last push: 2026-08-27T00:28:38+00:00

## Health v2 (maintenance only)
Score: 99/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 99, longevity 100
- inputs: {"age_days": 2854, "days_push": 7, "days_rel": 9, "gap_med": 18, "n_releases_24m": 28}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21654, forks 4176 (observed 2026-08-28T04:11:31.910622+00:00)

## What it is
ONNX Runtime is a cross-platform, high-performance machine-learning accelerator for running inference and training on ONNX models. It supports models from PyTorch, TensorFlow, and scikit-learn, and optimizes execution across CPU, GPU, and NPU hardware via an extensible execution-provider framework.

## Use cases
- run onnx models with high performance inference
- deploy pytorch models in c++ or c# apps
- accelerate transformer training on nvidia gpus
- run machine learning models on mobile and edge devices
- run llm inference locally in the browser
- speed up scikit-learn and xgboost model inference
- on-device training of models

## When to choose
- you need fast, production-grade inference across many platforms and languages
- you want to train in Python but deploy in C#, C++, Java, or JavaScript
- you need to leverage diverse hardware accelerators (CUDA, TensorRT, DirectML, CoreML, NNAPI, QNN) through one runtime
- you want to run generative AI or LLM models on-device for privacy and cost savings

## When to avoid
- your models stay in the original framework and framework-native inference is fast enough
- you need training features beyond what ORT's training support covers (e.g., complex custom training loops)
- you depend on a hardware accelerator only available as a preview or deprecated execution provider

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, llm-inference, deep-learning, gpu-computing, llm-training
- domain: machine-learning, deep-learning, large-language-models, artificial-intelligence, cross-platform
- platform: windows, browser, python, cpp, cross-platform, wasm
- tags: onnx, inference-engine, execution-providers, hardware-acceleration, model-optimization, edge-ai, pytorch, tensorflow, scikit-learn, directml, cuda, tensorrt, linux, macos, android, ios, gpu, nodejs

## Member repositories
- microsoft/onnxruntime (main) score 99

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:31.910622+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:57:50.811028+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/onnxruntime (fetched 2026-08-28T04:11:31.910622+00:00, sha db6e199afc58)
  - homepage: https://onnxruntime.ai (fetched 2026-08-29T07:56:30.022870+00:00, sha c1dde9324ee5)
  - site_page: https://onnxruntime.ai/getting-started (fetched 2026-08-29T07:56:30.032539+00:00, sha 41095031709c)
  - site_page: https://onnxruntime.ai/docs (fetched 2026-08-29T07:56:30.034382+00:00, sha 8a1d11f06987)
  - site_page: https://onnxruntime.ai/docs/tutorials (fetched 2026-08-29T07:56:30.037937+00:00, sha 688c60a5c379)
  - site_page: https://onnxruntime.ai/docs/install (fetched 2026-08-29T07:56:30.039528+00:00, sha d43bbe048fb0)
  - site_page: https://onnxruntime.ai/docs/execution-providers (fetched 2026-08-29T07:56:30.041368+00:00, sha 7488311f374c)
  - site_page: https://onnxruntime.ai/docs/get-started (fetched 2026-08-29T07:56:30.043110+00:00, sha ebeb27f91d2c)
  - site_page: https://onnxruntime.ai/docs/get-started/with-python (fetched 2026-08-29T07:56:30.044688+00:00, sha ec6f15fcd532)
  - site_page: https://onnxruntime.ai/generative-ai (fetched 2026-08-29T07:56:30.036205+00:00, sha c29818e75d88)
- Data as of 2026-08-30T08:39:29.467469+00:00.