未验证 提交 1616c32a 编写于 作者: Y Yiqun Liu 提交者: GitHub

Add the include of cudnn.h to enable the use of CUDNN_VERSION. (#15961)

test=develop
上级 79892545
......@@ -13,7 +13,9 @@
// limitations under the License.
#include "paddle/fluid/inference/api/paddle_pass_builder.h"
#ifdef PADDLE_WITH_CUDA
#include <cudnn.h>
#endif
#include <glog/logging.h>
namespace paddle {
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册