#144 · Primary category： Deep Learning Frameworks
TNN
A high-performance, lightweight cross-platform deep learning inference framework by Tencent, featuring model compression and code pruning.
Project last updated：05/09/25
GitHub Stars
4.6K
Forks
771
Contributors
81
License
Other
Why we included this project
TNN comes from Tencent's Youtu and Guangying labs, and it's built to run neural networks on devices where compute is tight. The framework builds on ncnn and Rapidnet, two earlier inference engines, and adds optimizations that make it a good fit for phones: the same runtime can also target x86 and NVIDIA GPUs for desktop and server work. It's been shipped inside Mobile QQ, Weishi, and Pitu, so the design has been shaped by real production use rather than just benchmarks. If your team needs to embed a model in a mobile app and also serve it elsewhere, TNN is worth a closer look.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
tensorflow
An Open Source Machine Learning Framework for Everyone
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras
Deep Learning for humans
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.