Merge branch 'develop' of https://github.com/ROCm/composable_kernel into update_cka8w8_uc

1b616990 · aska-0096 · af30d6b6 · 800cf897 · 1b616990 · 1b616990
Commit 1b616990 authored Feb 05, 2025 by aska-0096
20 changed files
--- a/include/ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_pipeline_problem.hpp
+++ b/include/ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_pipeline_problem.hpp
--- a/include/ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_pipeline_two_pass.hpp
+++ b/include/ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_pipeline_two_pass.hpp
--- a/include/ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_traits.hpp
+++ b/include/ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_traits.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_default_policy.hpp
+++ b/include/ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_default_policy.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_problem.hpp
+++ b/include/ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_problem.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/ops/softmax.hpp
+++ b/include/ck_tile/ops/softmax.hpp
--- a/include/ck_tile/ops/topk.hpp
+++ b/include/ck_tile/ops/topk.hpp
--- a/include/ck_tile/ops/topk_softmax.hpp
+++ b/include/ck_tile/ops/topk_softmax.hpp
--- a/include/ck_tile/ref/naive_attention.hpp
+++ b/include/ck_tile/ref/naive_attention.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_fpAintB_gemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_fpAintB_gemm.hpp
--- 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/reference_tensor_operation/cpu/reference_gemm_multiple_d.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_multiple_d.hpp
--- a/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
+++ b/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_b_scale.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_b_scale.hpp