Merge pull request #247 from ROCm/merge_from_public

Merge from public

Merge pull request #247 from ROCm/merge_from_public
Merge from public
5e93fa9e · Illia Silin · GitHub · 965b7ba4 · 2298a1a4 · 5e93fa9e
Unverified Commit 5e93fa9e authored Dec 10, 2024 by Illia Silin Committed by GitHub Dec 10, 2024
20 changed files
--- 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/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_universal_batched.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_batched.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/gemm_wmma.inc
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_wmma.inc
--- 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
--- a/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_bf16_bf16_bf16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_bf16_bf16_bf16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_bf16_bf16_bf16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_bf16_bf16_bf16_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_bf16_bf16_bf16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_bf16_bf16_bf16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_bf16_bf16_bf16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_bf16_bf16_bf16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_int8_int8_int8_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_int8_int8_int8_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_int8_int8_int8_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_int8_int8_int8_km_nk_mn_instance.cpp