merge develop to attn-train-develop-qloop

76f2b6cd · danyao12 · 9b4c780a · 1ee99dca · 76f2b6cd · 76f2b6cd
Commit 76f2b6cd authored Jul 14, 2023 by danyao12
20 changed files
--- a/library/include/ck/library/utility/convolution_parameter.hpp
+++ b/library/include/ck/library/utility/convolution_parameter.hpp
--- a/library/include/ck/library/utility/device_memory.hpp
+++ b/library/include/ck/library/utility/device_memory.hpp
--- a/library/include/ck/library/utility/fill.hpp
+++ b/library/include/ck/library/utility/fill.hpp
--- a/library/include/ck/library/utility/host_common_util.hpp
+++ b/library/include/ck/library/utility/host_common_util.hpp
--- a/library/include/ck/library/utility/host_conv.hpp
+++ b/library/include/ck/library/utility/host_conv.hpp
--- a/library/include/ck/library/utility/host_gemm.hpp
+++ b/library/include/ck/library/utility/host_gemm.hpp
--- a/library/include/ck/library/utility/host_reduction.hpp
+++ b/library/include/ck/library/utility/host_reduction.hpp
--- a/library/include/ck/library/utility/host_tensor.hpp
+++ b/library/include/ck/library/utility/host_tensor.hpp
--- a/library/include/ck/library/utility/host_tensor_generator.hpp
+++ b/library/include/ck/library/utility/host_tensor_generator.hpp
--- a/library/include/ck/library/utility/iterator.hpp
+++ b/library/include/ck/library/utility/iterator.hpp
--- a/library/include/ck/library/utility/literals.hpp
+++ b/library/include/ck/library/utility/literals.hpp
--- a/library/include/ck/library/utility/numeric.hpp
+++ b/library/include/ck/library/utility/numeric.hpp
--- a/library/include/ck/library/utility/op_instance_engine.hpp
+++ b/library/include/ck/library/utility/op_instance_engine.hpp
--- a/library/include/ck/library/utility/ranges.hpp
+++ b/library/include/ck/library/utility/ranges.hpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gkn_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gkn_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gnk_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gkm_gnk_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gkn_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gkn_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gnk_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_bf16_bf16_bf16_gmk_gnk_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm/device_batched_gemm_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp