add dispath_ffn_combine_bf16 (#5866)

### What this PR does / why we need it?
add dispath_ffn_combine_bf16

- vLLM version: v0.13.0
- vLLM main:
bde38c11df

---------

Signed-off-by: guanguan0308 <1546542263@qq.com>

csrc/dispatch_ffn_combine_bf16/op_kernel/utils/layout3d.hpp

@@ -0,0 +1,20 @@
+#ifndef LAYOUT_3D_HPP
+#define LAYOUT_3D_HPP
+#include "kernel_operator.h"
+#include "catlass/catlass.hpp"
+class Layout3D {
+    int64_t strides[2];
+    public:
+    CATLASS_DEVICE
+    Layout3D() {}
+    CATLASS_DEVICE
+    Layout3D(int64_t stride0, int64_t stride1) {
+        strides[0] = stride0;
+        strides[1] = stride1;
+    }
+    CATLASS_DEVICE
+    int64_t operator() (int64_t dim0, int64_t dim1, int64_t dim2) {
+        return dim0 * strides[0] + dim1 * strides[1] + dim2;
+    }
+};
+#endif // LAYOUT_3D_HPP