SGEMM repos (upstream_ref/sgemm_cuda/, 41 files): siboehm/SGEMM_CUDA: kernel 1-12, runner, CMake, cuBLAS benchmark wangzyon/NVIDIA_SGEMM_PRACTICE: kernel 1-7 (Chinese comments), utils edtallison/sgemm-cuda: kernel 01-09 (learning notes), Makefile xllm kernels (ex_engine/xllm_kernels/cuda/): fused_qknorm_rope.cu + bind — saves 128 kernel launches/fwd xattention/ — 6 files from upstream xllm headers: corex_compat_utils.h, topk_last_dim.cuh ilu/CMakeLists.txt SO_BUILD_MANIFEST.md — complete .so inventory and call chain analysis
29 lines
504 B
CMake
29 lines
504 B
CMake
include(cc_library)
|
|
set(CMAKE_CUDA_ARCHITECTURES ivcore11)
|
|
file(GLOB_RECURSE ILU_HEADER_FILES
|
|
"${CMAKE_CURRENT_LIST_DIR}/*.h"
|
|
)
|
|
|
|
file(GLOB_RECURSE ILU_SOURCE_FILES
|
|
"${CMAKE_CURRENT_LIST_DIR}/*.cpp"
|
|
"${CMAKE_CURRENT_LIST_DIR}/*.cu"
|
|
)
|
|
|
|
find_package(Python3 REQUIRED COMPONENTS Interpreter Development)
|
|
|
|
cc_library(
|
|
NAME
|
|
ilu_kernels
|
|
HDRS
|
|
${ILU_HEADER_FILES}
|
|
SRCS
|
|
${ILU_SOURCE_FILES}
|
|
DEPS
|
|
torch
|
|
:util
|
|
ixformer_kernels
|
|
ixformer
|
|
${Python3_LIBRARIES}
|
|
cuinfer
|
|
)
|