Merge remote-tracking branch 'origin/develop' into bwroblew/contraction_mixed_dt

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

@@ -89,6 +89,11 @@ list(APPEND GEMM_INSTANCES device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_ins
                            device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_kn_mn_instance.cpp
                            device_gemm_xdl_c_shuffle_bf16_bf16_bf16_km_nk_mn_instance.cpp)
 
+list(APPEND GEMM_INSTANCES device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_instance.cpp
+                           device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_nk_mn_instance.cpp
+                           device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_kn_mn_instance.cpp
+                           device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_nk_mn_instance.cpp)
+
 add_instance_library(device_gemm_instance ${GEMM_INSTANCES})
 
 set(ENABLE_PIPELINE_V2_OPT OFF)

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

 add_instance_library(device_grouped_conv1d_fwd_instance
-   device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
-   device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
-   device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
-   device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp
+   xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_bf16_instance.cpp
+   xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f16_instance.cpp
+   xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_f32_instance.cpp
+   xdl/device_grouped_conv1d_fwd_xdl_gnwc_gkxc_gnwk_int8_instance.cpp
 )