feat: add SYCL Backend Support for Intel GPUs (#330)

* update ggml and add SYCL CMake option

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

* hacky CMakeLists.txt for updating ggml in cpu backend

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

* rebase and clean code

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

* add sycl in README

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

* rebase ggml commit

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

* refine README

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

* update ggml for supporting sycl tsembd op

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

---------

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>
This commit is contained in:
zhentaoyu authored and GitHub committed 2024-08-10 13:42:50 +08:00
1 parent 5b8d16aa68
commit 697d000f49
8 files changed
+62 -10

No files matched your search

+9 -2
View File
@@ -27,19 +27,20 @@ option(SD_BUILD_EXAMPLES "sd: build examples" ${SD_STANDALONE})
option(SD_CUBLAS "sd: cuda backend" OFF)
option(SD_HIPBLAS "sd: rocm backend" OFF)
option(SD_METAL "sd: metal 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)
if(SD_CUBLAS)
message("Use CUBLAS as backend stable-diffusion")
message("Use CUBLAS as backend stable-diffusion")
set(GGML_CUDA ON)
add_definitions(-DSD_USE_CUBLAS)
endif()
if(SD_METAL)
message("Use Metal as backend stable-diffusion")
message("Use Metal as backend stable-diffusion")
set(GGML_METAL ON)
add_definitions(-DSD_USE_METAL)
endif()
@@ -53,6 +54,12 @@ if (SD_HIPBLAS)
endif()
endif ()
if(SD_SYCL)
message("Use SYCL as backend stable-diffusion")
set(GGML_SYCL ON)
add_definitions(-DSD_USE_SYCL)
endif()
if(SD_FLASH_ATTN)
message("Use Flash Attention for memory optimization")
add_definitions(-DSD_USE_FLASH_ATTENTION)