KellenSunderland commented on issue #12575: How to use tensorrt in FP16 or Int8 mode? URL: https://github.com/apache/incubator-mxnet/issues/12575#issuecomment-422902096 @lizhen2017 it can take some time to compile as it does some auto-tuning during engine creation. Would you like to see a feature that would allow you to cache the engine creation? If so I can add it to our backlog.
---------------------------------------------------------------- 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
