onnxruntime

{
  "aliases": [],
  "alternatives": [],
  "build_dependencies": [
    "boost",
    "cmake",
    "cpp-gsl",
    "eigen",
    "flatbuffers",
    "howard-hinnant-date",
    "nlohmann-json",
    "python@3.14",
    "safeint"
  ],
  "categories": [],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [
    "abseil",
    "onnx",
    "protobuf",
    "re2"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Cross-platform, high performance scoring engine for ML models",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:41:20+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "onnxruntime",
  "github_default_branch": "main",
  "github_last_commit_at": "2026-06-20T23:19:25Z",
  "github_readme_excerpt": "\u003cp align=\"center\"\u003e\u003cimg width=\"50%\" src=\"docs/images/ONNX_Runtime_logo_dark.png\" /\u003e\u003c/p\u003e\n\n**ONNX Runtime is a cross-platform inference and training machine-learning accelerator**.\n\n**ONNX Runtime inference** can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as PyTorch and TensorFlow/Keras as well as classical machine learning libraries such as scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different hardware, drivers, and operating systems, and provides optimal performance by leveraging hardware accelerators where applicable alongside graph optimizations and transforms. [Learn more \u0026rarr;](https://www.onnxruntime.ai/docs/#onnx-runtime-for-inferencing)\n\n**ONNX Runtime training** can accelerate the model training time on multi-node NVIDIA GPUs for transformer models with a one-line addition for existing PyTorch training scripts. [Learn more \u0026rarr;](https://www.onnxruntime.ai/docs/#onnx-runtime-for-training)\n\n## Get Started \u0026 Resources\n\n* **General Information**: [onnxruntime.ai](https://onnxruntime.ai)\n\n* **Usage documentation and tutorials**: [onnxruntime.ai/docs](https://onnxruntime.ai/docs)\n\n* **YouTube video tutorials**: [youtube.com/@ONNXRuntime](https://www.youtube.com/@ONNXRuntime)\n\n* [**Upcoming Release Roadmap**](https://onnxruntime.ai/roadmap)\n\n* **Companion sample repositories**:\n  - ONNX Runtime Inferencing: [microsoft/onnxruntime-inference-examples](https://github.com/microsoft/onnxruntime-inference-examples)\n  - ONNX Runtime Training: [microsoft/onnxruntime-training-examples](https://github.com/microsoft/onnxruntime-training-examples)\n\n* **Plugin EP repositories**:\n  - ONNX Runtime QNN Plugin EP: [onnxruntime/onnxruntime-qnn](https://github.com/onnxruntime/onnxruntime-qnn)\n\n## Releases\n\nThe current release and past releases can be found here: https://github.com/microsoft/onnxruntime/releases.\n\nFor details on the upcoming release, including release dates, announcements, featur",
  "github_repo": "microsoft/onnxruntime",
  "github_stars": 20873,
  "github_topics": [
    "ai-framework",
    "deep-learning",
    "hardware-acceleration",
    "machine-learning",
    "neural-networks",
    "onnx",
    "pytorch",
    "scikit-learn",
    "tensorflow"
  ],
  "homepage": "https://github.com/microsoft/onnxruntime",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 1483,
  "installs_365d": 12536,
  "installs_90d": 4417,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "MIT",
  "llm_generated_at": null,
  "llm_model": null,
  "name": "onnxruntime",
  "oldnames": [],
  "one_liner": null,
  "optional_dependencies": [],
  "rank_30d": 1114,
  "rank_365d": 1308,
  "rank_90d": 1158,
  "raw_hash": "8f7bc4640e636276",
  "recommended_dependencies": [],
  "revision": 0,
  "ruby_source_path": "Formula/o/onnxruntime.rb",
  "tap": "homebrew/core",
  "test_dependencies": [],
  "uses_from_macos": [],
  "version_head": null,
  "version_stable": "1.27.0",
  "versioned_formulae": [],
  "why_use_this": null
}