DickJC123 opened a new pull request #7425: Tensorcore fullyconnected support
URL: https://github.com/apache/incubator-mxnet/pull/7425
   Adds TensorCore algo support to the FullyConnected operator for users with 
NVIDIA Volta / cuda9 / cudnn7.  On by default, this can be disabled through an 
environment variable as in:
   Applies to float16 I/O instances only.
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:

With regards,
Apache Git Services

Reply via email to