ref(upstream): FULL TREE — Deep-Spark xllm (1470) + ds_vllm csrc/models (703)

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

upstream_ref/xllm/cmake/CMakeMUSAInformation.cmake

@@ -0,0 +1,18 @@
+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)