Tao Lv
Tao Lv
> so that at every mini-batch we end up with pretty much unique problem size ranging from 512x100 to 512x10000 elements and this is why we would like to use...
I think the random number generator is taking a significant part in the execution of dropout. That's why we optimized it in MXNet with `viRngBernoulli` from VSL. But now `viRngBernoulli`...
I notice there is a [RFC](https://github.com/oneapi-src/oneDNN/pull/760) opened for this request. You may want to take a look. @eric-haibin-lin @apeforest @pengzhao-intel
@szha Is this change good to you?
Hi @seujung thank you for the contribution. Do you mind putting code and document directly in folder, instead of having a git submodule?
Thank you for adding this! This needs to modify the config.cmake carefully if we want to build binary for another platform, ie. using cmake for the convenient releases.
It would also change the default behavior of cmake build - previously it can be built on a machine and run on a lower end machine, but now it probably...
@leezu Could you please rebase? Then we can merge if CI passes. Because I see the last validation is 7 days ago.
@niuxiaog > The op list is roughly the supported ops list of graph compiler. That's internal. Users don't know which ops are supported by graph compiler from API. > Models...
The proposal was reviewed internally and will not be implemented in the library as the use scenario in frameworks is not clear. Thank you all for the discussions and participation.