TNN
A cross-platform deep learning inference framework for diverse computing environments, from mobile to desktop and server.
GraphCanon updated 2w · GitHub synced 2w · 27 views this month
Decision brief
Developed by Tencent Labs, TNN offers strong cross-platform performance with efficient model compression and runtime optimization for mobile to server use.
Good fit when
- When developing AI apps for Tencent-affiliated software like Mobile QQ or Weishi
- For projects requiring high-performance inference across ARM devices with extensive acceleration solutions support
Avoid when
- If you prefer a framework that heavily integrates with TensorFlow's ecosystem, as TNN has a steeper learning curve when converting models
- When your project primarily relies on Python environments. TNN is C++-centric with no native Python interface.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (452d since push)
- As of 2w
- Provenance
- Not a fork · Organization account
- As of 2w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
git clone https://github.com/Tencent/TNNSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Developed by Tencent's Youtu Lab and Guangying Lab, TNN is an advanced inference tool that supports model conversion, compilation, and runtime across various platforms. It excels in high performance, efficient model compression, and code optimization.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Aug 4, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Aug 4, 2026
- Languages
- c++
Source: github.language · Aug 4, 2026
Categories
Tags
README
Quick Start
It is very simple to use TNN. If you have a trained model, the model can be deployed on the target platform through three steps.
-
Convert the trained model into a TNN model. We provide a wealth of tools to help you complete this step, whether you are using Tensorflow, Pytorch, or Caffe, you can easily complete the conversion. Detailed hands-on tutorials can be found here How to Create a TNN Model.
-
When you have finished converting the model, the second step is to compile the TNN engine of the target platform. You can choose among different acceleration solutions such as ARM/OpenCL/Metal/NPU/X86/CUDA according to the hardware support. For these platforms, TNN provides convenient one-click scripts to compile. For detailed steps, please refer to How to Compile TNN.
-
The final step is to use the compiled TNN engine for inference. You can make program calls to TNN inside your application. We provide a rich and detailed demo as a reference to help you complete.
- Run an iOS Demo
- Run an Android Demo
- Run an Linux/Windows Demo
For agents
This page has a .md twin and JSON over the API.