/bolt

Bolt is a deep learning library with high performance and heterogeneous flexibility.

Primary LanguageC++MIT LicenseMIT

Introduction


License: MIT

Bolt is a light-weight library for deep learning. Bolt, as a universal deployment tool for all kinds of neural networks, aims to minimize the inference runtime as much as possible. Bolt has been widely deployed and used in many departments of HUAWEI company, such as 2012 Laboratory, CBG and HUAWEI Product Lines. If you have questions or suggestions, you can submit issue. QQ群: 833345709

Why Bolt is what you need?


  • High Performance: 15%+ faster than existing open source acceleration libraries.
  • Rich Model Conversion: support Caffe, ONNX, TFLite, Tensorflow.
  • Various Inference Precision: support FP32, FP16, INT8, 1-BIT.
  • Multiple platforms: ARM CPU(v7, v8, v8.2), Mali GPU, Qualcomm GPU, X86 CPU(AVX2, AVX512)
  • Bolt is the first to support NLP and also supports common CV applications.
  • Minimize ROM/RAM
  • Rich Graph Optimization
  • Efficient Thread Affinity Setting
  • Auto Algorithm Tuning
  • Time-Series Data Acceleration

See more excellent features and details here

Building Status


Kinds of choices are provided for the compilation of bolt. Please make a suitable choice depending on your environment.

target platform build command Linux Windows MacOS
Android(armv7) ./install.sh --target=android-armv7 Build Status Build Status Build Status
Android(armv8+gpu) ./install.sh --target=android-aarch64 --gpu Build Status Build Status Build Status
Android(x86_64) ./install.sh --target=android-x86_64 Build Status Build Status Build Status
iOS(armv7) ./install.sh --target=ios-armv7 / / Build Status
iOS(armv8) ./install.sh --target=ios-aarch64 / / Build Status
Linux(X86_64) ./install.sh --target=linux-x86_64 Build Status / /
Linux(x86_64_avx2) ./install.sh --target=linux-x86_64_avx2 Build Status / /
Windows(X86_64) ./install.sh --target=windows-x86_64 / Build Status /
Windows(x86_64_avx2) ./install.sh --target=windows-x86_64_avx2 / Build Status /
MacOS(X86_64) ./install.sh --target=macos-x86_64 / / Build Status
MacOS(x86_64_avx2) ./install.sh --target=macos-x86_64_avx2 / / Build Status

NOTE: Bolt defaultly link static library, This may cause some problem on some platforms. You can use --shared option to link shared library.

Quick Start


Two steps to get started with bolt.
  1. Conversion: use X2bolt to convert your model from caffe,onnx,tflite or tensorflow to .bolt;

  2. Inference: run benchmark with .bolt and data to get the inference result.

    For more details about the usage of X2bolt and benchmark tools, see docs/USER_HANDBOOK.md.

DL Applications in Bolt

Here we show some interesting and useful applications in bolt.

Face Detection ASR Semantics Analysis Image Classification
face_detection demo_link: face detection asr demo_link: asr semantics analysis demo_link: semantics analysis image_classification demo_link: image classification

Verified Networks


Bolt has shown its high performance in the inference of common CV and NLP neural networks. Some of the representative networks that we have verified are listed below. You can find detailed benchmark information in docs/BENCHMARK.md.

Application Models
CV Resnet50, Shufflenet, Squeezenet, Densenet, Efficientnet, Mobilenet_v1, Mobilenet_v2, Mobilenet_v3, BiRealNet, ReActNet, Ghostnet, SSD, Yolov3, Pointnet, ViT, TNT ...
NLP Bert, Albert, Neural Machine Translation, Text To Speech, Automatic Speech Recognition, Tdnn ...
Recommendation MLP
More DL Tasks ...

More models than these mentioned above are supported, users are encouraged to further explore.

Documentations


Everything you want to know about bolt is recorded in the detailed documentations stored in docs.

Articles


教程


Acknowledgement


Bolt refers to the following projects: caffe, onnx, tensorflow, ncnn, mnn, dabnn.

License


The MIT License(MIT)