Skip to content

Open deep learning compiler stack for Kendryte AI accelerator

License

Notifications You must be signed in to change notification settings

HeJunchao100813/nncase

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

nncase

GitHub repository Gitee repository GitHub release

nncase is a neural network compiler for AI accelerators.

nncase 是一个为 AI 加速器设计的神经网络编译器。

技术交流 QQ 群:790699378

Telegram: nncase community

Install from binaries

从二进制安装

Download prebuilt binaries from Release.

下载预编译的二进制文件 Release

Build from source

从源码编译

Build from source

Supported operators

支持的算子

K210/K510

K230

Resources

资源

K210


Architecture

架构

nncase arch

Features

  • Supports multiple inputs and outputs and multi-branch structure
  • Static memory allocation, no heap memory acquired
  • Operators fusion and optimizations
  • Support float and quantized uint8 inference
  • Support post quantization from float model with calibration dataset
  • Flat model with zero copy loading

功能

  • 支持多输入输出网络,支持多分支结构
  • 静态内存分配,不需要堆内存
  • 算子合并和优化
  • 支持 float 和量化 uint8 推理
  • 支持训练后量化,使用浮点模型和量化校准集
  • 平坦模型,支持零拷贝加载

About

Open deep learning compiler stack for Kendryte AI accelerator

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C# 56.9%
  • C++ 31.0%
  • Python 9.2%
  • CMake 1.4%
  • C 1.2%
  • HTML 0.2%
  • Other 0.1%