add flash attn support check

[leejet]

fix #802

[Green-Sky]

Will test in a sec.

update1: works with cuda again. (6 images in 523.34s, similar to before)
update2: vulkan still works. (6 images in 205.99s, slower but I also started it heat soaked)
update3: reran vulkan with a little cooled down system (6 images in 183.43s)

[Green-Sky]

I more and more wish the whole architecture was more llama.cpp like.