Merge branch 'develop' into amd-develop

7f65ac05 · Jun Liu · 687d2b7e · 7e5c81fe · 7f65ac05 · 7f65ac05
Commit 7f65ac05 authored Apr 04, 2024 by Jun Liu
20 changed files
--- 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_fixed_nk/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
--- 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
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/quantization/CMakeLists.txt
--- a/profiler/include/profiler/profile_grouped_conv_fwd_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_conv_fwd_impl.hpp
--- a/profiler/include/profiler/profile_grouped_gemm_two_stage_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_gemm_two_stage_impl.hpp
--- a/profiler/include/profiler/profile_permute_scale_impl.hpp
+++ b/profiler/include/profiler/profile_permute_scale_impl.hpp
--- a/profiler/src/CMakeLists.txt
+++ b/profiler/src/CMakeLists.txt