Token-Picker: Accelerating Attention in Text Generation with Minimized Memory Transfer via Probability Estimation.
Junyoung Park, Myeonggu Kang, Yunki Han, Yanggon Kim, Jaekang Shin, Lee-Sup Kim
Browse the full DAC paper archive.
Junyoung Park, Myeonggu Kang, Yunki Han, Yanggon Kim, Jaekang Shin, Lee-Sup Kim
Browse the full DAC paper archive.