microsoft/onnxruntime

onnxruntime

✅ 近期有维护

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

22,209Stars
4,394Forks
+44近 7 天 Star

C++ · MIT · 最近推送 2026-11-02

官方仓库与安装文档 ↗
deep-learningonnxneural-networksmachine-learningai-frameworkhardware-accelerationpytorchtensorflowscikit-learn

Star 历史

2025-09-292026-11-02
查看历史数据
日期Stars
2026-10-0421,992
2026-10-0522,000
2026-10-0622,007
2026-10-0722,016
2026-10-0822,018
2026-10-0922,022
2026-10-1022,029
2026-10-1122,034
2026-10-1222,045
2026-10-1322,059
2026-10-1422,065
2026-10-1522,073
2026-10-1622,085
2026-10-1722,093
2026-10-1822,099
2026-10-1922,104
2026-10-2022,112
2026-10-2122,125
2026-10-2222,136
2026-10-2322,143
2026-10-2422,156
2026-10-2522,164
2026-10-2622,169
2026-10-2722,174
2026-10-2822,181
2026-10-2922,188
2026-10-3022,197
2026-10-3122,201
2026-11-0122,210
2026-11-0222,209

获取项目

git clone https://github.com/microsoft/onnxruntime.git

相关项目与平替候选

同领域不等于功能完全相同，选型前请核对官方文档和许可证。

ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

★ 44,174MNN

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

★ 16,335xgboost

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C and more. Runs on single machine, Hadoop, Spark

★ 28,934