eric-haibin-lin opened a new issue #14073: Fp16 support for layernorm URL: https://github.com/apache/incubator-mxnet/issues/14073 Currently, given fp16 inputs, nd.LayerNorm/sym.LayerNorm perform reduction in fp16, which losses precision. The reduction should be done in fp32 instead. @sxjscience
---------------------------------------------------------------- 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
