Hi, I have some relatively large models, a few GB in size. It takes some time for Moses to load an entire model (phrase table, reordering table, etc.) into memory. I wonder whether preloading these models into memory (using vmtouch or RAM disk) will help speed it up.
Many thanks, Guchun
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
