Merge branch 'develop' into grouped_gemm_multi_abd_fixed_nk_example

70eebf22 · zjing14 · GitHub · 5608328c · 98fd41f5 · 70eebf22
Unverified Commit 70eebf22 authored Nov 07, 2023 by zjing14 Committed by GitHub Nov 07, 2023
20 changed files
--- a/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_elementwise_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp
--- a/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp
--- a/include/ck/utility/data_type.hpp
+++ b/include/ck/utility/data_type.hpp
--- a/include/ck/utility/f8_utils.hpp
+++ b/include/ck/utility/f8_utils.hpp
--- a/include/ck/utility/inner_product.hpp
+++ b/include/ck/utility/inner_product.hpp
--- a/include/ck/utility/math.hpp
+++ b/include/ck/utility/math.hpp
--- a/include/ck/utility/math_v2.hpp
+++ b/include/ck/utility/math_v2.hpp
--- a/include/ck/utility/statically_indexed_array_multi_index.hpp
+++ b/include/ck/utility/statically_indexed_array_multi_index.hpp
--- a/include/ck/utility/type_convert.hpp
+++ b/include/ck/utility/type_convert.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp