Fix too relaxed check on CUDA "fast copy" (can_be_transposed) condition

Author: pwilkin

ggml/src/ggml-cuda/cpy.cu

@@ -384,7 +384,8 @@ void ggml_cuda_cpy(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, gg
     char * src1_ddc = (char *) src1->data;
 
     const bool contiguous_srcs = ggml_is_contiguous(src0) && ggml_is_contiguous(src1);
-    const bool can_be_transposed = nb01 == (int64_t)ggml_element_size(src0) && src0->ne[3] == 1;
+    const bool can_be_transposed = nb01 == (int64_t)ggml_element_size(src0) && 
+        src0->ne[3] == 1 && nb02 == ne00 * ne01 * (int64_t)ggml_element_size(src0);
 
     if (src0->type == src1->type && contiguous_srcs) {
         GGML_ASSERT(ggml_nbytes(src0) == ggml_nbytes(src1));