fix: repair flash attention support (#386)

* repair flash attention in _ext
this does not fix the currently broken fa behind the define, which is only used by VAE

Co-authored-by: FSSRepo <FSSRepo@users.noreply.github.com>

* make flash attention in the diffusion model a runtime flag
no support for sd3 or video

* remove old flash attention option and switch vae over to attn_ext

* update docs

* format code

---------

Co-authored-by: FSSRepo <FSSRepo@users.noreply.github.com>
Co-authored-by: leejet <leejet714@gmail.com>

CMakeLists.txt

@@ -29,7 +29,6 @@ option(SD_HIPBLAS                    "sd: rocm backend" OFF)
 option(SD_METAL                      "sd: metal backend" OFF)
 option(SD_VULKAN                     "sd: vulkan backend" OFF)
 option(SD_SYCL                       "sd: sycl backend" OFF)
-option(SD_FLASH_ATTN                 "sd: use flash attention for x4 less memory usage" OFF)
 option(SD_FAST_SOFTMAX               "sd: x1.5 faster softmax, indeterministic (sometimes, same seed don't generate same image), cuda only" OFF)
 option(SD_BUILD_SHARED_LIBS          "sd: build shared libs" OFF)
 #option(SD_BUILD_SERVER               "sd: build server example"                           ON)
@@ -61,11 +60,6 @@ if (SD_HIPBLAS)
     endif()
 endif ()
 
-if(SD_FLASH_ATTN)
-    message("-- Use Flash Attention for memory optimization")
-    add_definitions(-DSD_USE_FLASH_ATTENTION)
-endif()
-
 set(SD_LIB stable-diffusion)
 
 file(GLOB SD_LIB_SOURCES