sync from the public repo

e599063f · illsilin · 5dbbf5d6 · 566b6480 · e599063f · e599063f
Commit e599063f authored May 10, 2024 by illsilin
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_km_kn_mn_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_km_kn_mn_common.hpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_kn_mn_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_kn_mn_common.hpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_nk_mn_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_nk_mn_common.hpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bias_gelu_bf16_i8_bf16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bias_gelu_bf16_i8_bf16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bias_gelu_bf16_i8_bf16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bias_gelu_bf16_i8_bf16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bias_gelu_bf16_i8_bf16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk_multi_abd/device_grouped_gemm_xdl_fixed_nk_bias_gelu_bf16_i8_bf16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_multiply_bf16_i8_bf16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_multiply_bf16_i8_bf16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_instances.cpp