everwind commented on issue #3946: When predicting, does mxnet provide thread-safe interface? URL: https://github.com/apache/incubator-mxnet/issues/3946#issuecomment-324198209 I think we should separate "data" and the model weights . when predicting, each thread can share the model weights and use different data . In this way , we have mush less memory consumption . In practice, we often train the model on GPUS, but use the model on the cpu machine. so it is very important to provide the effective multi-thread prediction ---------------------------------------------------------------- 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: us...@infra.apache.org
With regards, Apache Git Services