Merge remote-tracking branch 'origin/develop' into ck_tile/moe

54d3e2f1 · carlushuang · 199f7f71 · b8addae2 · 54d3e2f1 · 54d3e2f1
Commit 54d3e2f1 authored Sep 01, 2024 by carlushuang
18 changed files
--- a/library/include/ck/library/tensor_operation_instance/gpu/permute_scale.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/permute_scale.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.hpp
--- a/library/include/ck/library/utility/check_err.hpp
+++ b/library/include/ck/library/utility/check_err.hpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/xdl/device_grouped_conv3d_fwd_xdl_combconvscale_ndhwgc_gkzyxc_ndhwgk_f8_f8_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale/xdl/device_grouped_conv3d_fwd_xdl_combconvscale_ndhwgc_gkzyxc_ndhwgk_f8_f8_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/xdl/device_grouped_conv3d_fwd_xdl_combconvscale_relu_ndhwgc_gkzyxc_ndhwgk_f8_f8_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/xdl/device_grouped_conv3d_fwd_xdl_combconvscale_relu_ndhwgc_gkzyxc_ndhwgk_f8_f8_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/xdl/device_grouped_conv3d_fwd_xdl_convscale_relu_ndhwgc_gkzyxc_ndhwgk_f8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_convscale_relu/xdl/device_grouped_conv3d_fwd_xdl_convscale_relu_ndhwgc_gkzyxc_ndhwgk_f8_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_6d_fp32_fp8_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_fp32_fp8_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32_amax.cpp
--- a/profiler/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_conv_bwd_weight_impl.hpp
--- a/profiler/src/profile_grouped_conv_bwd_weight.cpp
+++ b/profiler/src/profile_grouped_conv_bwd_weight.cpp
--- a/script/convert_miopen_driver_to_profiler.py
+++ b/script/convert_miopen_driver_to_profiler.py
--- a/test/data_type/CMakeLists.txt
+++ b/test/data_type/CMakeLists.txt
--- a/test/data_type/test_bf8.cpp
+++ b/test/data_type/test_bf8.cpp
--- a/test/data_type/test_fp8.cpp
+++ b/test/data_type/test_fp8.cpp