Page History

...

The above diagram includes the current threading model during inference as I understand it.  The most important thing to note here is that when we run inference or read a result we must do it on a single main thread (aka dispatcher thread).  It’s therefore very important that we block this thread as little as possible.  This is not a problem when we’re submitting predictions, we can call forward on a symbol as many times as we like.  Each forward call will quickly kick off a computation graph that will eventually be executed in the engine.

...

https://discuss.mxnet.io/t/mxnet-crashing-likely-memory-corruption/121

https://github.com/apache/incubator-mxnet/pull/8887