Merge branch 'develop' into gfx950

ef5e60f6 · illsilin · 2cc0fa26 · 5e93fa9e · ef5e60f6 · ef5e60f6
Commit ef5e60f6 authored Dec 11, 2024 by illsilin
20 changed files
--- 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/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