fix: remove glog/cuda_ops_api.h dependency from all xllm CUDA kernels

cuda_ops_api.h includes glog/logging.h and ATen/DynamicLibrary.h
which are not available in corex standalone compilation.

All kernel .cu files only need device_utils.cuh (provides namespace,
XLLM_KERNEL_ATTR macro, CUB includes, type helpers).

Fixed files:
  norm.cu, activation.cu, rope.cu, block_copy.cu, reshape_paged_cache.cu
  moe/moe_combine.cu, moe/moe_compute_index.cu, moe/moe_fused_topk.cu

ex_engine/xllm_kernels/cuda/norm.cu

@@ -19,7 +19,6 @@ limitations under the License.
 #include <cstdint>
 #include <cub/cub.cuh>
 
-#include "cuda_ops_api.h"
 #include "device_utils.cuh"
 #include "fp8_quant_utils.cuh"
 #include "type_convert.cuh"
@@ -27,14 +26,10 @@ limitations under the License.
 // ref to:
 // https://github.com/vllm-project/vllm/blob/main/csrc/layernorm_kernels.cu
 
-#if CUB_VERSION >= 200800
-// corex CUB (CUDA 10.2) — no cuda::std::functional
+// corex CUB (CUDA 10.2) — use old-style CUB operators
 using CubAddOp = cub::Sum;
 using CubMaxOp = cub::Max;
-#else   // if CUB_VERSION < 200800
-using CubAddOp = cub::Sum;
-using CubMaxOp = cub::Max;
-#endif  // CUB_VERSION
+
 
 namespace {