QueensGambit commented on issue #16173: Saving and loading cudNN autotune and graph optimization URL: https://github.com/apache/incubator-mxnet/issues/16173#issuecomment-537972862 @chinakook This is an option, but could violate the ability to deploy the same model across different platforms (e.g. CPU, CPU-MKLDNN, GPU-CUDA, GPU-TensorRT).
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to 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
