batch=1,why adapter latency so much vs. LoRA in paper??? about lora

[edwardjhu]

This is because when the bsz is small, we need to parallelize over width to gain the best hardware efficiency. Adapter adds to the depth, which has to be processed sequentially.

[barvin04]

This is because when the bsz is small, we need to parallelize over width to gain the best hardware efficiency. Adapter adds to the depth, which has to be processed sequentially.

@edwardjhu Can you please explain this in layman terms?

[macqueen09]

in Lora paper , we can see adapter in batch=1 can make a 20% latency.
why?
so little parameter can make a so huge latency.