Merge branch 'develop' of https://github.com/ROCm/composable_kernel into update_cka8w8

c8c016dd · aska-0096 · e8ca3daf · 4e731776 · c8c016dd · c8c016dd
Commit c8c016dd authored Dec 13, 2024 by aska-0096
20 changed files
--- a/include/ck_tile/ops/gemm/pipeline/gemm_pipeline_agmem_bgmem_creg_v1_default_policy.hpp
+++ b/include/ck_tile/ops/gemm/pipeline/gemm_pipeline_agmem_bgmem_creg_v1_default_policy.hpp
--- a/include/ck_tile/ops/gemm/pipeline/gemm_pipeline_problem.hpp
+++ b/include/ck_tile/ops/gemm/pipeline/gemm_pipeline_problem.hpp
--- a/include/ck_tile/ops/gemm/warp/warp_gemm.hpp
+++ b/include/ck_tile/ops/gemm/warp/warp_gemm.hpp
--- a/include/ck_tile/ops/gemm/warp/warp_gemm_attribute_mfma.hpp
+++ b/include/ck_tile/ops/gemm/warp/warp_gemm_attribute_mfma.hpp
--- a/include/ck_tile/ops/gemm/warp/warp_gemm_attribute_mfma_impl.hpp
+++ b/include/ck_tile/ops/gemm/warp/warp_gemm_attribute_mfma_impl.hpp
--- a/include/ck_tile/ops/gemm/warp/warp_gemm_dispatcher.hpp
+++ b/include/ck_tile/ops/gemm/warp/warp_gemm_dispatcher.hpp
--- a/include/ck_tile/ops/gemm/warp/warp_gemm_impl.hpp
+++ b/include/ck_tile/ops/gemm/warp/warp_gemm_impl.hpp
--- a/include/ck_tile/ops/smoothquant.hpp
+++ b/include/ck_tile/ops/smoothquant.hpp
--- a/include/ck_tile/ops/smoothquant/kernel/moe_smoothquant_kernel.hpp
+++ b/include/ck_tile/ops/smoothquant/kernel/moe_smoothquant_kernel.hpp
--- a/include/ck_tile/ops/smoothquant/kernel/smoothquant_kernel.hpp
+++ b/include/ck_tile/ops/smoothquant/kernel/smoothquant_kernel.hpp
--- a/include/ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_one_pass.hpp
+++ b/include/ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_one_pass.hpp
--- a/include/ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_two_pass.hpp
+++ b/include/ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_two_pass.hpp
--- a/include/ck_tile/ref/README.md
+++ b/include/ck_tile/ref/README.md
--- a/include/ck_tile/ref/naive_attention.hpp
+++ b/include/ck_tile/ref/naive_attention.hpp
--- a/include/ck_tile/remod.py
+++ b/include/ck_tile/remod.py
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_streamk.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_streamk.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_irregular_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/CMakeLists.txt