• Li Zhang's avatar
    Unify prefill & decode passes (#775) · 7f943a26
    Li Zhang authored
    * Unify prefill and decode passes
    
    * dynamic split-fuse
    
    * refactor
    
    * correct input count calculation
    
    * remove unused
    
    * lint
    
    * lint
    
    * fix msvc build
    
    * fix msvc build
    
    * fix msvc build
    
    * fix msvc build
    
    * fix msvc build
    
    * fix msvc build
    
    * fix msvc build
    
    * fix msvc build
    
    * fix msvc build
    7f943a26
bert_preprocess_kernels.cu 7.64 KB