Skip to content
Ashok Bhat edited this page Nov 11, 2020 · 9 revisions

About

Features

  • Multiple algorithms for convolutional layers:
    • Fast convolution based on Fourier transform (for kernels up to 16x16 without stride)
    • Fast convolution based on Winograd transform (for 3x3 kernels without stride)
    • Implicit matrix-matrix multiplication algorithm (no limitations)
    • Direct convolution algorithm (for 1x1 kernels without stride)
  • Multi-threaded SIMD-aware implementations of neural network layers

Development status

A comment in GitHub - NNPACK is not actively developed anymore and XNNPACK is the successor and is in my experience faster (as well as having a better and more complete interface)

Usage

Frameworks

  • PyTorch - On mobile for inference in convolutional layers.
  • TVM - for inference in convolutional layers
  • MXNet - for inference in convolutional layers, fully-connected, and max-pooling layers.

End users

  • Facebook - in production.
  • Prisma - in the mobile app

See also

Clone this wiki locally