Replaces cherry-picked upstream_ref with complete source trees. xllm/ — Iluvatar official C++ inference engine (15MB, 1470 files) Complete: kernels → layers → models → runtime → scheduler → api Excluded: .git, binary images, third_party submodule checkouts ds_vllm/ — Iluvatar official vllm fork (8MB, 703 files) Included: csrc/ (ALL CUDA kernels), fused_moe/, qwen3_5 model, _custom_ops Excluded: tests, benchmarks, docs, examples (not needed for reference) Critical call chains now fully traceable: MoE: moe_topk_softmax_kernels.cuh → ixformer.h → fused_moe.cpp → layer GDN: qwen3_gated_delta_net_base.cpp → qwen3_5_gated_delta_net.cpp Attention: ixformer.h → xllm_paged_attention → attention.cpp
18 lines
480 B
CMake
18 lines
480 B
CMake
set(CMAKE_MUSA_SOURCE_FILE_EXTENSIONS mu;cu)
|
|
if(UNIX)
|
|
set(CMAKE_MUSA_OUTPUT_EXTENSION .o)
|
|
else()
|
|
set(CMAKE_MUSA_OUTPUT_EXTENSION .obj)
|
|
endif()
|
|
|
|
set(CMAKE_INCLUDE_FLAG_MUSA "-I")
|
|
|
|
set(CMAKE_MUSA_COMPILE_OBJECT
|
|
"<CMAKE_MUSA_COMPILER> <DEFINES> <INCLUDES> <FLAGS> -mtgpu -c <SOURCE> -o <OBJECT>"
|
|
)
|
|
|
|
set(CMAKE_MUSA_LINK_EXECUTABLE
|
|
"<CMAKE_MUSA_COMPILER> <FLAGS> <LINK_FLAGS> <OBJECTS> -lmusa -lmusart -o <TARGET> <LINK_LIBRARIES>"
|
|
)
|
|
|
|
set(CMAKE_MUSA_INFORMATION_LOADED 1) |