★
onnxruntime 是用 C++ 编写的 AI 工具，用于人工智能方向的建模与推理，主打高性能、跨平台。
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Tencent / TNN
TNN
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contrib
TNN 是用 C++ 编写的学习资料，用于系统学习与查阅，主打高性能、跨平台、开源免费。
目前累计 4.7k star、771 fork，主要语言为 C++，项目始于 2020 年，采用 NOASSERTION 许可。最近状态：已有一段时间未更新。适合：想补齐某块知识的开发者。
中文介绍优先采用本站人工维护条目；无维护条目时依据 GitHub 公开字段（语言、主题、星标、提交时间）自动生成，未经项目方确认，不构成选型结论。Tencent/TNN 是一个以 C++ 为主的开源项目，目前累计 4.7k star、771 fork，一年以上有维护。主要方向：coreml、深度学习、face-detection、hairsegmentaion、inference、mnn。
依据 GitHub 公开字段（语言、主题、星标、提交时间）自动生成，未经人工逐项核实。README
正在加载…相关项目
★
TensorRT 是用 C++ 编写的学习资料，用于系统学习与查阅，主打高性能、开源免费。
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of Tens…
★
MNN 是用 C++ 编写的学习资料，用于系统学习与查阅，主打高性能、速度快、轻量。
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
★
ncnn 是用 C++ 编写的 AI 工具，用于人工智能方向的建模与推理，主打高性能。
ncnn is a high-performance neural network inference framework optimized for the mobile platform
★
DeepSpeech 是用 C++ 编写的 AI 工具，用于人工智能方向的建模与推理，主打开源免费、实时。
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4…
★
mediapipe 是用 C++ 编写的 AI 工具，用于人工智能方向的建模与推理，主打可扩展、跨平台。
Cross-platform, customizable ML solutions for live and streaming media.