Merge branch 'develop' into universal_streamk

909f519c · Harisankar Sadasivan · GitHub · 406fa265 · 3bb0fe6c · 909f519c
Unverified Commit 909f519c authored Jun 27, 2024 by Harisankar Sadasivan Committed by GitHub Jun 27, 2024
20 changed files
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_combine_kernel.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_combine_kernel.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_combine_tile_partitioner.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_combine_tile_partitioner.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_kernel.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_kernel.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_tile_partitioner.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_tile_partitioner.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_combine_pipeline.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_combine_pipeline.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_combine_pipeline_default_policy.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_combine_pipeline_default_policy.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_pipeline_qr_ks_vs.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_pipeline_qr_ks_vs.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_pipeline_qr_ks_vs_async.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_pipeline_qr_ks_vs_async.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_pipeline_qr_ks_vs_async_default_policy.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_pipeline_qr_ks_vs_async_default_policy.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_pipeline_qr_ks_vs_default_policy.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_fwd_splitkv_pipeline_qr_ks_vs_default_policy.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_problem.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_problem.hpp
--- a/include/ck_tile/ops/fmha/pipeline/tile_fmha_traits.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/tile_fmha_traits.hpp
--- a/library/include/ck/library/utility/fill.hpp
+++ b/library/include/ck/library/utility/fill.hpp
--- a/library/src/tensor_operation_instance/gpu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/CMakeLists.txt
--- a/profiler/src/CMakeLists.txt
+++ b/profiler/src/CMakeLists.txt
--- a/test/CMakeLists.txt
+++ b/test/CMakeLists.txt
--- a/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp
+++ b/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp
--- a/test/smfmac_op/CMakeLists.txt
+++ b/test/smfmac_op/CMakeLists.txt
+add_gtest_executable(test_smfmac_op smfmac_op_xdl.cpp)
+target_link_libraries(test_smfmac_op PRIVATE utility)
--- a/test/smfmac_op/smfmac_op.cpp
+++ b/test/smfmac_op/smfmac_op.cpp
--- a/test/smfmac_op/smfmac_op_util.hpp
+++ b/test/smfmac_op/smfmac_op_util.hpp