Merge branch 'develop' into normalization/splitK

97e851e5 · rocking5566 · GitHub · 9c42a83a · fc26d42a · 97e851e5
Unverified Commit 97e851e5 authored Apr 17, 2023 by rocking5566 Committed by GitHub Apr 17, 2023
20 changed files
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/device_grouped_gemm_fastgelu_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/normalization/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_groupnorm_swish_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm2d_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_layernorm4d_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_normalization_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_normalization_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_normalization_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_normalization_f32_instance.cpp