TensorRT icon indicating copy to clipboard operation
TensorRT copied to clipboard

Published 20 hours ago • verified publisher icon NVIDIA

how to support FlashAttention2?

Open echosyy opened this issue 6 months ago • 1 comments

Hi, does the currently transferred trt engine support flash focus2 by default? If it is not supported by default, how should I use fa2 in the output engine? Thanks,

echosyy avatar Aug 15 '24 09:08 echosyy