Cached Transformers: Improving Transformers with Differentiable Memory Cache.

Zhaoyang Zhang Wenqi Shao Yixiao Ge Xiaogang Wang Jinwei Gu Ping Luo

Published in: CoRR (2023)

Keyphrases

main memory
memory hierarchy
partial discharge
cache conscious
computing power
resource consumption
response time
prefetching
memory space
database
hit rate
memory usage
memory management
multithreading
cached data
memory subsystem
query processing