| CPC G06F 12/123 (2013.01) | 16 Claims |
|
1. A method for model selection for swapping between a first memory and a second memory, the method comprising:
sorting models in a first list, the first list including models loaded in the first memory, wherein sorting is based at least in part on a least recently used (LRU) of each model;
removing duplicate models, if any, from within a second list of models, the second list including models to be loaded into the first memory;
determining an eviction score of each of the models based at least in part on: a size of the particular model, a last time the particular model was used in the first list and an index position of the particular model in the second list;
selecting a model from the first list having a highest eviction score compared with other models in the first list; and
swapping the selected model from the first memory to the second memory.
|