Merge branch 'develop' into codegen-enable-hiprtc

2a30cfdd · arai713 · GitHub · 9533a172 · 78195ccc · 2a30cfdd
Unverified Commit 2a30cfdd authored Feb 12, 2025 by arai713 Committed by GitHub Feb 12, 2025
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_two_stage_xdl_ndhwgc_gkzyxc_ndhwgk_f16_pipev5_irregular_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/xdl/device_grouped_conv3d_bwd_weight_two_stage_xdl_ndhwgc_gkzyxc_ndhwgk_f16_pipev5_irregular_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_irregular_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_irregular_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_bf16_bf16_bf16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_bf16_bf16_bf16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_bf16_bf16_bf16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_bf16_bf16_bf16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_multiply_bf16_i8_bf16_mk_kn_mn.hpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_multiply_bf16_i8_bf16_mk_kn_mn.hpp
--- a/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f8_instance.cpp
--- a/library/src/utility/CMakeLists.txt
+++ b/library/src/utility/CMakeLists.txt
--- a/modified_files.txt
+++ b/modified_files.txt
--- a/profiler/README.md
+++ b/profiler/README.md
--- a/profiler/include/profiler/profile_batched_gemm_b_scale_impl.hpp
+++ b/profiler/include/profiler/profile_batched_gemm_b_scale_impl.hpp
--- a/profiler/include/profiler/profile_batched_gemm_bias_softmax_gemm_permute_impl.hpp
+++ b/profiler/include/profiler/profile_batched_gemm_bias_softmax_gemm_permute_impl.hpp
--- a/profiler/include/profiler/profile_batched_gemm_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_batched_gemm_gemm_impl.hpp
--- a/profiler/include/profiler/profile_batched_gemm_softmax_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_batched_gemm_softmax_gemm_impl.hpp
--- a/profiler/include/profiler/profile_batched_gemm_softmax_gemm_permute_impl.hpp
+++ b/profiler/include/profiler/profile_batched_gemm_softmax_gemm_permute_impl.hpp
--- a/profiler/include/profiler/profile_gemm_b_scale_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_b_scale_impl.hpp
--- a/profiler/include/profiler/profile_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_impl.hpp
--- a/profiler/include/profiler/profile_gemm_universal_batched_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_universal_batched_impl.hpp
--- a/profiler/include/profiler/profile_gemm_universal_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_universal_impl.hpp