microsoft /onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
★ 22,317⑂ 4,449👁 264⑃ 21,801● 8,895▤ 92
More from this author
+11
Daily
+99
Weekly
+262
Monthly
22,317
stars
4,449
forks
264
watchers
21,801
prs
8,895
issues
92
releases
README
ONNX Runtime is a cross-platform inference and training machine-learning accelerator. 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 → 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 → Get Started & Resources General Information: onnxruntime.ai Usage documentation and tutorials: onnxruntime.ai/docs YouTube video tutorials: youtube.com/@ONNXRuntime Upcoming Release Roadmap Companion sample repositories: - ONNX Runtime Inferencing: microsoft/onnxruntime-inference-examples - ONNX Runtime Training: microsoft/onnxruntime-training-examples Plugin EP repositories: - ONNX Runtime QNN Plugin EP: onnxruntime/onnxruntime-qnn Releases The current release and past releases can be found here: https://github.com/microsoft/onnxruntime/releases. For details on the upcoming release, including release dates, announcements, features, and guidance on submitting feature requests, please visit the release roadmap: https://onnxruntime.ai/roadmap. Data/Telemetry This project may collect usage data and send it to Microsoft to help improve our products and services. See the privacy statement for more details. Contributions and Feedback We welcome contributions! Please see the contribution guidelines. For feature requests or bug reports, please file a GitHub Issue. For general discussion or questions, please use GitHub Discussions. Code of Conduct This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments. License This project is licensed under the MIT License.
Top issues
#20876[Web] WebGPU and WASM Backends Unavailable within Service Worker67 comments · 2024-05-30#16121EfficientNMS_TRT missing attribute class_agnostic w/ TensorRT 8.635 comments · 2023-05-26#28284Cara - Cara Membatalkan Pinjaman Akulaku31 comments · 2026-04-30#19846C# I need to run the program on NPU (OnnxRuntime + DirectML + NPU),but it failed30 comments · 2024-03-11#14997[Feature Request] 4bit and 2bit and 1bit quantization support30 comments · 2023-03-10#9313ONNXRuntime CPU - Memory spiking continuously (Memory leak)27 comments · 2021-10-08#886onnxruntime slower than xgboost & lightgbm in batch predictions27 comments · 2019-04-23#21917[Feature Request] Add vulkan execution provider26 comments · 2024-08-29
Discussions
#34225How do I install the CUDA thingie?10 comments · 2026-11-14#34187MIGraphX EP2 comments · 2026-11-13#34073Orange Pi Zero 3W (12 GB) – Complete power-off during ONNX Runtime / Piper TTS inference1 comments · 2026-11-10#33878YOLOVAL: local game-image checks with ONNX Runtime CPU (paid model showcase)0 comments · 2026-11-04#33737Proposal: a browser model diagnostics workbench with exportable reproductions1 comments · 2026-10-29#33665Release-bound dependency resolution and native provenance for onnxruntime-win-x64 1.29.0 CPU package1 comments · 2026-10-28#33637edge-nix: Packaging ONNX Runtime for edge devices using Nix (Arduino UNO Q)0 comments · 2026-10-27#33488[email protected] Windows x64:已发布原生文件对应的第三方告知与来源材料1 comments · 2026-10-20
Latest release
ONNX Runtime v1.32.0 v1.32.0 2026-11-13ONNX Runtime 1.32.0 reintegrates ONNX 1.23.2 with opset 28 support, introduces CPU/GPU hybrid MoE offloading and shared-layout CPU QMoE kernels, expands device-memory, weightless-compilation, and Python model-package APIs, dramatically accelerates session initialization on large graphs, and strengthens runtime and optimizer reliability. These notes cover changes since ONNX Runtime 1.31.1. CUDA and WebGPU kernel updates are summarized here; detailed provider notes are covered by their separate plugin EP releases. Highlights - Reintegrated ONNX 1.23.2 with opset 28 operator support (Space