feat: ggml-alloc integration and gpu acceleration (#75)

* set ggml url to FSSRepo/ggml

* ggml-alloc integration

* offload all functions to gpu

* gguf format + native converter

* merge custom vae to a model

* full offload to gpu

* improve pretty progress

---------

Co-authored-by: leejet <leejet714@gmail.com>

CMakeLists.txt

@@ -24,10 +24,24 @@ endif()
 # general
 #option(SD_BUILD_TESTS                "sd: build tests"    ${SD_STANDALONE})
 option(SD_BUILD_EXAMPLES             "sd: build examples" ${SD_STANDALONE})
+option(SD_CUBLAS                     "sd: cuda backend" OFF)
+option(SD_FLASH_ATTN            "sd: use flash attention for x4 less memory usage" OFF)
 option(BUILD_SHARED_LIBS             "sd: build shared libs" OFF)
 #option(SD_BUILD_SERVER               "sd: build server example"                           ON)
 
+if(SD_CUBLAS)
+	message("Use CUBLAS as backend stable-diffusion")
+    set(GGML_CUBLAS ON)
+    add_definitions(-DSD_USE_CUBLAS)
+endif()
 
+if(SD_FLASH_ATTN)
+    message("Use Flash Attention for memory optimization")
+    add_definitions(-DSD_USE_FLASH_ATTENTION)
+endif()
+
+
+set(CMAKE_POLICY_DEFAULT_CMP0077 NEW)
 # deps
 add_subdirectory(ggml)
 
@@ -38,6 +52,7 @@ target_link_libraries(${SD_LIB} PUBLIC ggml)
 target_include_directories(${SD_LIB} PUBLIC .)
 target_compile_features(${SD_LIB} PUBLIC cxx_std_11)
 
+add_subdirectory(common)
 
 if (SD_BUILD_EXAMPLES)
     add_subdirectory(examples)