FrozenGene opened a new issue #5216: [AutoTVM] RPCRunner network overhead URL: https://github.com/apache/incubator-tvm/issues/5216 When we use AutoTVM to tune on remote devices, we will introduce data copy to remote devices and bring network overhead: https://github.com/apache/incubator-tvm/blob/9d2c984ab633b372cd31054a5abd84a2e16f6220/python/tvm/autotvm/measure/measure_methods.py#L484 To solve this, we could implement a `tvm.nd.non_empty` in the tvm runtime, then we can do the random fill on the target device without copying over the network. I have implemented one version of it and plan to port it to upstream. Open this to track this issue.
---------------------------------------------------------------- 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
