• oahzxl's avatar
    Optimize long sequence inference memory (#69) · 3429e62d
    oahzxl authored
    * update ops
    
    * finish on 1 gpu
    
    * update bug in incom mul
    
    * update async broadcast
    
    * update income
    
    * add attention chunk
    
    * finish embed
    
    * align evoformer
    
    * update embed
    
    * align evoformer
    
    * update embed
    
    * update template
    
    * update template
    
    * update extramsa
    
    * fix a bug
    
    * update outerproductmean
    
    * remove useless class
    
    * fix a bug when chunk is None
    
    * fix bug when chunk is None
    3429e62d
embedders.py 9.93 KB