qnnpack: Quantized Neural Networks PACKage
Contents
Overview of package
Package: | qnnpack |
---|---|
Description: | Quantized Neural Networks PACKage |
For more information: | https://github.com/facebookincubator/gloo |
Categories: | |
License: | OpenSource (BSD) |
General usage information
The Quantized Neural Networks PACKage (QNNPack) is a mobile-optimized library for low-precision high-performance neural network inference. QNNPACK provides implementation of common neural network operators on quantized 8-bit tensors.
QNNPACK is not intended to be directly used by machine learning researchers; instead it provides low-level performance primitives for high-level deep learning frameworks.
The following environmental variables have been defined:
- \$QNNPACK_ROOT has been set to the root of the qnnpack installation
- \$QNNPACK_LIBDIR points to the directory containing the libraries
- \$QNNPACK_INCDIR points to the directory containing the header files
You will probably wish to use these by adding the following flags to your compilation command (e.g. to CFLAGS in your Makefile):
- -I\$QNNPACK_INCDIR
- -L\$QNNPACK_LIBDIR -Wl,-rpath,\$QNNPACK_LIBDIR
Available versions of the package qnnpack, by cluster
This section lists the available versions of the package qnnpackon the different clusters.
Available versions of qnnpack on the Deepthought2 cluster (RHEL8)
Version | Module tags | CPU optimized for | GPU ready? |
---|---|---|---|
2019-08-28 | qnnpack/2019-08-28 | ivybridge | N |
master | qnnpack/master | x86_64 | N |
Available versions of qnnpack on the Juggernaut cluster
Version | Module tags | CPU optimized for | GPU ready? |
---|---|---|---|
2019-08-28 | qnnpack/2019-08-28 | broadwell | N |