resolved conflicts

library/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(GEMM_MULTIPLY_ADD_INSTANCES)
 list(APPEND GEMM_MULTIPLY_ADD_INSTANCES device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
                                         device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_reduce/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_reduce_instance
     device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
     device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp

library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(GEMM_SPLITK_INSTANCES)
 
 list(APPEND GEMM_SPLITK_INSTANCES 

library/src/tensor_operation_instance/gpu/gemm_streamk/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_gemm_streamk_instance
    # device_gemm_xdl_streamk_f32_f32_f32_mk_kn_mn_instance.cpp
    # device_gemm_xdl_streamk_f32_f32_f32_mk_nk_mn_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv1d_bwd_weight/CMakeLists.txt

+# ONLY XDL_AND_DL_KERNELS
 set(GROUPED_CONV1D_BWD_WEIGHT
     xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
     xdl/device_grouped_conv1d_bwd_weight_xdl_gnwc_gkxc_gnwk_f32_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv1d_fwd/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_grouped_conv1d_fwd_instance
    xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
    xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt

+# ONLY XDL_AND_WMMA_KERNELS
 add_instance_library(
 	device_grouped_conv2d_bwd_data_instance
 	xdl/device_grouped_conv2d_bwd_data_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_weight/CMakeLists.txt

+# ONLY XDL_AND_DL_KERNELS
 set(GROUPED_CONV2D_BWD_WEIGHT
     xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
     xdl/device_grouped_conv2d_bwd_weight_xdl_gnhwc_gkyxc_gnhwk_f32_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt

+# XDL_DL_WMMA_KERNELS
 add_instance_library(device_grouped_conv2d_fwd_instance
    #xdl
    # GNHWC, GKYXC, GNHWK

library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data/CMakeLists.txt

+# ONLY XDL_AND_WMMA_KERNELS
 set(GROUPED_CONV3D_BWD_DATA
    xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
    xdl/device_grouped_conv3d_bwd_data_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_bilinear/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(GROUPED_CONV3D_BWD_DATA_BILINEAR
    xdl/device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
    xdl/device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_scale/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(GROUPED_CONV3D_BWD_DATA_BILINEAR
    xdl/device_grouped_conv3d_bwd_data_xdl_scale_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
    xdl/device_grouped_conv3d_bwd_data_xdl_scale_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt

+# XDL_DL_WMMA_KERNELS
 set(GROUPED_CONV3D_BWD_WEIGHT
     xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
     xdl/device_grouped_conv3d_bwd_weight_xdl_gndhwc_gkzyxc_gndhwk_f32_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt

+# ONLY XDL_AND_WMMA_KERNELS
 set(GROUPED_CONV3D_FWD
    xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_bf16_instance.cpp
    xdl/device_grouped_conv3d_fwd_xdl_gndhwc_gkzyxc_gndhwk_f16_instance.cpp
@@ -40,4 +41,9 @@ if(DTYPES MATCHES "bf8" OR NOT DEFINED DTYPES)
       xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_bf8_instance.cpp)
 endif()
 
+if((DTYPES MATCHES "fp8" AND DTYPES MATCHES "bf8") OR NOT DEFINED DTYPES)
+    list(APPEND GROUPED_CONV3D_FWD
+      xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_fp8_bf8_instance.cpp)
+endif()
+
 add_instance_library(device_grouped_conv3d_fwd_instance ${GROUPED_CONV3D_FWD})

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_fp8_bf8_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f8_bf8_instances(
+    std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
+                                                                NDHWGC,
+                                                                GKZYXC,
+                                                                Empty_Tuple,
+                                                                NDHWGK,
+                                                                F8,
+                                                                BF8,
+                                                                Empty_Tuple,
+                                                                F8,
+                                                                PassThrough,
+                                                                PassThrough,
+                                                                PassThrough,
+                                                                F8,
+                                                                BF8>>>& instances)
+{
+    add_device_operation_instances(instances,
+                                   device_grouped_conv_fwd_xdl_f8_bf8_instances<3,
+                                                                                NDHWGC,
+                                                                                GKZYXC,
+                                                                                Empty_Tuple,
+                                                                                NDHWGK,
+                                                                                ConvFwdDefault>{});
+    add_device_operation_instances(instances,
+                                   device_grouped_conv_fwd_xdl_f8_bf8_instances<3,
+                                                                                NDHWGC,
+                                                                                GKZYXC,
+                                                                                Empty_Tuple,
+                                                                                NDHWGK,
+                                                                                ConvFwd1x1P0>{});
+    add_device_operation_instances(instances,
+                                   device_grouped_conv_fwd_xdl_f8_bf8_instances<3,
+                                                                                NDHWGC,
+                                                                                GKZYXC,
+                                                                                Empty_Tuple,
+                                                                                NDHWGK,
+                                                                                ConvFwd1x1S1P0>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(GROUPED_CONV3D_FWD_BILINEAR
    xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
    xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_scale/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(GROUPED_CONV3D_FWD_BILINEAR
    xdl/device_grouped_conv3d_fwd_xdl_scale_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
    xdl/device_grouped_conv3d_fwd_xdl_scale_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_scaleadd_ab/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(GROUPED_CONV3D_FWD_SCALEADD_AB
    xdl/device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
    xdl/device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_scaleadd_scaleadd_relu/CMakeLists.txt

+# ONLY XDL_KERNELS
 set(GROUPED_CONV3D_FWD_scaleadd_scaleadd_RELU
    xdl/device_grouped_conv3d_fwd_xdl_scaleadd_scaleadd_relu_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
    xdl/device_grouped_conv3d_fwd_xdl_scaleadd_scaleadd_relu_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp

library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt

+# ONLY XDL_KERNELS
 add_instance_library(device_grouped_gemm_instance
    device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
    device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp