[ANNOUNCE] Apache SINGA 3.2.0 released

[zhaojing Luo <zh...@comp.nus.edu.sg>]

We are pleased to announce that SINGA 3.2.0 was released on 15 August 2021.

SINGA is a general distributed deep learning library
for training big deep learning models over large datasets.

The release is available at: http://singa.apache.org/docs/downloads/

The main features of this release include

    1. Enhance distributed training.
    2. Add Support for half-precision floating-point format (fp16) in deep
learning models and computational kernels.
    3. Update new onnx APIs and fix onnx examples accordingly, namely,
DenseNet121, ShuffleNetv1, ShuffleNetv2, SqueezeNet, VGG19.
    4. Add a new method to resize images by given width and height.
    5. Use docusaurus versioning to simplify the process of generating the
project homepage.

We look forward to hearing your feedback, suggestions, and contributions to
the project.

Best Regards,
Zhaojing
(On behalf of the SINGA team)