feat: add sd3.5 support (#445) #594

Job	Run time
ubuntu-latest-cmake	1m 17s
macOS-latest-cmake	1m 32s
windows-latest-cmake (noavx, -DGGML_AVX=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF -DSD_BUILD_SHARED_LIBS...	2m 15s
windows-latest-cmake (avx2, -DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON)	2m 32s
windows-latest-cmake (avx, -DGGML_AVX2=OFF -DSD_BUILD_SHARED_LIBS=ON)	2m 8s
windows-latest-cmake (avx512, -DGGML_AVX512=ON -DSD_BUILD_SHARED_LIBS=ON)	1m 31s
windows-latest-cmake (cuda12, -DSD_CUBLAS=ON -DSD_BUILD_SHARED_LIBS=ON)	1h 23m 8s
windows-latest-cmake (rocm5.5, -G Ninja -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DS...	29m 21s
windows-latest-cmake (vulkan, -DSD_VULKAN=ON -DSD_BUILD_SHARED_LIBS=ON)	2m 39s
release	47s
	2h 7m 10s

Provide feedback