update include file name

include/ck/tensor_operation/gpu/device/impl/device_batched_mha_fwd_xdl_cshuffle.hpp

@@ -9,7 +9,7 @@
 #include "ck/utility/common_header.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
-#include "ck/tensor_operation/gpu/device/device_batched_multiple_head_flash_attention_fwd.hpp"
+#include "ck/tensor_operation/gpu/device/device_batched_mha_infer.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/matrix_padder.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_fwd_xdl_cshuffle.hpp

@@ -10,7 +10,7 @@
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/device_grouped_multiple_head_flash_attention_fwd.hpp"
+#include "ck/tensor_operation/gpu/device/device_grouped_mha_infer.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/matrix_padder.hpp"
 #include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_fwd_xdl_cshuffle.hpp"
@@ -231,7 +231,7 @@ struct DeviceGroupedMultiheadAttentionForward_Xdl
 #endif
 
     using DeviceOp    = DeviceGroupedMultiheadAttentionForward_Xdl;
-    using ProblemDesc = typename DeviceGroupedMultiheadAttentionForward<NumDimG,
+    using ProblemDesc = typename DeviceGroupedMultiheadAttentionInfer<NumDimG,
                                                                       NumDimM,
                                                                       NumDimN,
                                                                       NumDimK,