This is a software decoder designed to run on general purpose hardware.
Adding custom hardware like tensor cores to the stack would serves a different use case.
Adding custom hardware like tensor cores to the stack would serves a different use case.
What I'm saying is the performance problem is a "code smell". The algorithms are getting so complicated that perhaps we are approaching fundamental limits of heuristiccs; we might get better + faster results ditching "smart" algorithms and just learning the codec in a much higher dimensional space.
Again specialized hardware, but a different approach to it.