Merge branch 'develop' into gemm_elementwise_gemm

3c5717df · Illia Silin · GitHub · 171b9030 · d9f1ead3 · 3c5717df
Unverified Commit 3c5717df authored Feb 10, 2025 by Illia Silin Committed by GitHub Feb 10, 2025
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_v2.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_v2.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_multiple_d_splitk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_multiple_d_splitk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_tile_loop.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_tile_loop.hpp
--- a/include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/codegen_device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/codegen_device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_e_permute_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_e_permute_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_xdl_cshuffle_v3.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_xdl_cshuffle_v3.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp