• Lei Wang's avatar
    [Langauge] Support n>256 for v2 (#1182) · b66a93c5
    Lei Wang authored
    * fix
    
    * lint fix
    
    * fix
    
    * lint fix
    
    * fix
    
    * upd
    
    * support n>256
    
    * Remove unnecessary pass configurations for fast math in MHA forward BHSD latency script.
    
    * lint fix
    
    * lint fix
    b66a93c5
correctness_evaluation.py 20.7 KB