Merge branch 'develop' into amd-develop

c5ad2e80 · Jun Liu · 4b798833 · 489c78d0 · c5ad2e80 · c5ad2e80
Commit c5ad2e80 authored Nov 12, 2024 by Jun Liu
20 changed files
--- a/include/ck_tile/ops/rmsnorm2d.hpp
+++ b/include/ck_tile/ops/rmsnorm2d.hpp
--- a/include/ck_tile/ops/rmsnorm2d/kernel/rmsnorm2d_fwd_kernel.hpp
+++ b/include/ck_tile/ops/rmsnorm2d/kernel/rmsnorm2d_fwd_kernel.hpp
--- a/include/ck_tile/ops/rmsnorm2d/kernel/rmsnorm2d_fwd_shape.hpp
+++ b/include/ck_tile/ops/rmsnorm2d/kernel/rmsnorm2d_fwd_shape.hpp
--- a/include/ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_pipeline_default_policy.hpp
+++ b/include/ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_pipeline_default_policy.hpp
--- a/include/ck_tile/ops/smoothquant.hpp
+++ b/include/ck_tile/ops/smoothquant.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/welford/block/block_welford.hpp
+++ b/include/ck_tile/ops/welford/block/block_welford.hpp
--- a/include/ck_tile/ops/welford/block/block_welford_problem.hpp
+++ b/include/ck_tile/ops/welford/block/block_welford_problem.hpp
--- a/include/ck_tile/ops/welford/thread/thread_welford.hpp
+++ b/include/ck_tile/ops/welford/thread/thread_welford.hpp
--- a/include/ck_tile/remod.py
+++ b/include/ck_tile/remod.py
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_two_stage_xdl_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_two_stage_xdl_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_comp_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_comp_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_dynamic_op_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_dynamic_op_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_large_tensor_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_large_tensor_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_mem_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_mem_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_merged_groups_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_merged_groups_instance.hpp