[Optimization] optmize tritonmoe_preprocess op (#7687)

* opt moe_align_kernel

Author: yongqiangma

custom_ops/gpu_ops/helper.h

@@ -75,6 +75,8 @@ namespace cub = hipcub;
 using json = nlohmann::json;
 #endif
 
+#define CEILDIV(a, b) (((a + b - 1) / b))
+
 #define CUDA_CHECK(call)                           \
   do {                                             \
     const cudaError_t error_code = call;           \