You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
1、There is currently a trt acceleration model task, but it uses flash atten and the function used is flash_attn_varlen_qkvpacked_func, but I can't find how it works.
2、Is it possible to provide an equivalent python implementation?
The text was updated successfully, but these errors were encountered:
1、There is currently a trt acceleration model task, but it uses flash atten and the function used is flash_attn_varlen_qkvpacked_func, but I can't find how it works.
2、Is it possible to provide an equivalent python implementation?
The text was updated successfully, but these errors were encountered: