Merge remote-tracking branch 'origin/develop' into ck_tile/layernorm_fusion

55cdf2b9 · carlushuang · 4b59b5c9 · b098b71b · 55cdf2b9 · 55cdf2b9
Commit 55cdf2b9 authored Oct 27, 2024 by carlushuang
12 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_dynamic_op/xdl/device_grouped_conv3d_fwd_xdl_dynamic_op_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_dynamic_op/xdl/device_grouped_conv3d_fwd_xdl_dynamic_op_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_dynamic_op/xdl/device_grouped_conv3d_fwd_xdl_dynamic_op_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_dynamic_op/xdl/device_grouped_conv3d_fwd_xdl_dynamic_op_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_dynamic_op/xdl/device_grouped_conv3d_fwd_xdl_dynamic_op_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_dynamic_op/xdl/device_grouped_conv3d_fwd_xdl_dynamic_op_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp
--- a/profiler/include/profiler/profile_gemm_multiply_multiply_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_multiply_multiply_impl.hpp
--- a/profiler/include/profiler/profile_pool3d_fwd_impl.hpp
+++ b/profiler/include/profiler/profile_pool3d_fwd_impl.hpp
--- a/profiler/src/profile_gemm_multiply_multiply.cpp
+++ b/profiler/src/profile_gemm_multiply_multiply.cpp
--- a/profiler/src/profile_grouped_conv_bwd_weight.cpp
+++ b/profiler/src/profile_grouped_conv_bwd_weight.cpp
--- a/python/ck4inductor/grouped_conv_fwd/gen_instances.py
+++ b/python/ck4inductor/grouped_conv_fwd/gen_instances.py
--- a/python/ck4inductor/grouped_conv_fwd/op.py
+++ b/python/ck4inductor/grouped_conv_fwd/op.py
--- a/python/ck4inductor/universal_gemm/gen_instances.py
+++ b/python/ck4inductor/universal_gemm/gen_instances.py
--- a/python/ck4inductor/universal_gemm/op.py
+++ b/python/ck4inductor/universal_gemm/op.py
--- a/python/ck4inductor/util.py
+++ b/python/ck4inductor/util.py