diff options
Diffstat (limited to 'ggml/src/CMakeLists.txt')
-rw-r--r-- | ggml/src/CMakeLists.txt | 25 |
1 files changed, 23 insertions, 2 deletions
diff --git a/ggml/src/CMakeLists.txt b/ggml/src/CMakeLists.txt index 14650d03..9872b3de 100644 --- a/ggml/src/CMakeLists.txt +++ b/ggml/src/CMakeLists.txt @@ -258,8 +258,29 @@ set (GGML_HEADERS_IQK iqk/iqk_config.h) if (GGML_IQK_MUL_MAT) message(STATUS "Using optimized iqk matrix multiplications") add_compile_definitions(GGML_USE_IQK_MULMAT) - set(GGML_SOURCES_IQK_MM iqk/iqk_mul_mat.cpp iqk/iqk_flash_attn.cpp) - set(GGML_HEADERS_IQK_MM iqk/iqk_mul_mat.h iqk/iqk_flash_impl.h) + set(GGML_SOURCES_IQK_MM iqk/iqk_mul_mat.cpp + iqk/iqk_flash_attn.cpp + iqk/fa/iqk_fa_576_512.cpp + iqk/fa/iqk_fa_192_128.cpp + iqk/fa/iqk_fa_256_256.cpp + iqk/fa/iqk_fa_128_128.cpp + iqk/fa/iqk_fa_96_96.cpp + iqk/fa/iqk_fa_64_64.cpp + iqk/iqk_gemm_floats.cpp + iqk/iqk_gemm_kquants.cpp + iqk/iqk_gemm_iquants.cpp + iqk/iqk_gemm_iqk_quants.cpp + iqk/iqk_gemm_1bit.cpp + iqk/iqk_gemm_legacy_quants.cpp) + set(GGML_HEADERS_IQK_MM iqk/iqk_mul_mat.h + iqk/iqk_flash_impl.h + iqk/fa/iqk_fa_templates.h + iqk/iqk_gemm_floats.h + iqk/iqk_gemm_kquants.h + iqk/iqk_gemm_iquants.h + iqk/iqk_gemm_iqk_quants.h + iqk/iqk_gemm_1bit.h + iqk/iqk_gemm_legacy_quants.h) if (GGML_IQK_FLASH_ATTENTION) message(STATUS "Enabling IQK Flash Attention kernels") add_compile_definitions(GGML_IQK_FLASH_ATTENTION) |