szhengac opened a new issue #11796: Batch_dot does not support FP16 well URL: https://github.com/apache/incubator-mxnet/issues/11796 The `batch_dot` does not support FP16 well and can make training slower compared to using FP32. This is tested using [Transformer](https://github.com/dmlc/gluon-nlp/blob/master/scripts/nmt/train_transformer.py) model in Gluonnlp. This feature has been added in a [NVIDIA mxnet](https://docs.nvidia.com/deeplearning/dgx/mxnet-release-notes/rel_17.11.html#rel_17.11). So I think it is good to enable this in the master.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
