TNN Versions Save

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. Contributions are welcome to work in collaborative with us and make TNN a better framework.

v0.3.0

3 years ago
  • support intel X86 and Nvidia GPU
  • add more op support for nlp model, like lstm and bert
  • add more demos for android/ios/linux/macos/windows
  • add const folder in runtime mode
  • add github action release for continuous delivery
  • optimeze kernel for arm(armv8.2-fp16), opencl(autotune)
  • fix some bugs about compilation, tools and runtime execution