Move Device Ops implementations into impl directory. (#777)

Co-authored-by: Adam Osewski <aosewski@amd.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>

library/src/tensor_operation_instance/gpu/quantization/conv2d_fwd/device_conv2d_dl_int8_instance.hpp

@@ -4,7 +4,7 @@
 #pragma once
 
 #include "conv2d_quantization_common.hpp"
-#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
 
 namespace ck {
 namespace tensor_operation {

test/gemm/instance/gemm_wavelet_f16_tn_instance.cpp

@@ -5,7 +5,7 @@
 
 #include "ck/ck.hpp"
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
-#include "ck/tensor_operation/gpu/device/device_gemm_xdl_waveletmodel_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_waveletmodel_cshuffle.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"