Merge pull request #285 from ROCm/merge_from_public

Merge from public

Merge pull request #285 from ROCm/merge_from_public
Merge from public
5063a39f · Illia Silin · GitHub · bfdc2430 · 96a0d5f6 · 5063a39f
Unverified Commit 5063a39f authored Jan 17, 2025 by Illia Silin Committed by GitHub Jan 17, 2025
20 changed files
--- 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
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_dl.inc
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_dl.inc
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_dpp.inc
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_dpp.inc
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_multiply_multiply.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_multiply_multiply.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.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_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_convolution_backward_weight.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight_xdl.inc
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight_xdl.inc
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward.hpp