[dayeye2006]

I think no optimization is possible withoutprofiling. I think getting yourself familiar with the tools to understand the performance of a model might be the 1st step, e.g., https://pytorch.org/tutorials/recipes/recipes/profiler_recip...

[tanelpoder]

Yes - understand first, then fix. And you’ll understand by measuring/profiling things.

I’d also recommend the detailed pytorch optimization case studies by Paul Bridger:

https://paulbridger.com/