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/ds_vllm/csrc/cuda_utils.h

@@ -0,0 +1,41 @@
+#pragma once
+
+#include <stdio.h>
+
+#if defined(__HIPCC__)
+  #define HOST_DEVICE_INLINE __host__ __device__
+  #define DEVICE_INLINE __device__
+  #define HOST_INLINE __host__
+#elif defined(__CUDACC__) || defined(_NVHPC_CUDA)
+  #define HOST_DEVICE_INLINE __host__ __device__ __forceinline__
+  #define DEVICE_INLINE __device__ __forceinline__
+  #define HOST_INLINE __host__ __forceinline__
+#else
+  #define HOST_DEVICE_INLINE inline
+  #define DEVICE_INLINE inline
+  #define HOST_INLINE inline
+#endif
+
+#define CUDA_CHECK(cmd)                                             \
+  do {                                                              \
+    cudaError_t e = cmd;                                            \
+    if (e != cudaSuccess) {                                         \
+      printf("Failed: Cuda error %s:%d '%s'\n", __FILE__, __LINE__, \
+             cudaGetErrorString(e));                                \
+      exit(EXIT_FAILURE);                                           \
+    }                                                               \
+  } while (0)
+
+int64_t get_device_attribute(int64_t attribute, int64_t device_id);
+
+int64_t get_max_shared_memory_per_block_device_attribute(int64_t device_id);
+
+namespace cuda_utils {
+
+template <typename T>
+HOST_DEVICE_INLINE constexpr std::enable_if_t<std::is_integral_v<T>, T>
+ceil_div(T a, T b) {
+  return (a + b - 1) / b;
+}
+
+};  // namespace cuda_utils