Codebook-Based Acceleration for Ternary Language Model Inference.
Tomas Sousa Pereira, Ruibao Wang, Ikenna Nwozo, Haoran Geng, X. Sharon Hu
Browse the full ISLPED paper archive.
Tomas Sousa Pereira, Ruibao Wang, Ikenna Nwozo, Haoran Geng, X. Sharon Hu
Browse the full ISLPED paper archive.