Open mattare2 opened 2 years ago
Have the authors considered any approaches to reduce the latency of this approach?
Would be interested to understand if any avenues have been pursued (e.g., distilling into a more performant architecture)
Thanks!
Have the authors considered any approaches to reduce the latency of this approach?
Would be interested to understand if any avenues have been pursued (e.g., distilling into a more performant architecture)
Thanks!