Saving and loading cudNN autotune and graph optimization

Hello everyone,

I created a feature request on GitHub about the topic of saving cudNN autotune and graph fusion to disk in order to be reloaded later:

In our use case TensorRT is very helpful but requires a long start-up time.
This start-up time leads to the point that our executable is being killed by external programs because it does not reply in time to ping requests.

Is anyone interested in this feature, too?

Best,
~QueensGambit

Thanks for creating the feature request. A similar request has been opened a while ago: https://github.com/apache/incubator-mxnet/issues/10567 It would be certainly helpful to cache autotune results.

1 Like