Skip to content

GitLab

"...composable_kernel_rocm.git" did not exist on "1fd27d520f6aaa54c20cd6cc4439fb9c9f60c508"
Unverified Commit d20c472f authored by Dan Yao's avatar Dan Yao Committed by GitHub
Browse files

Merge pull request #834 from ROCmSoftwarePlatform/mha-train-develop-tinyfix 

Remove un-necessary including in the FlashAttention device operators
parents 1ab31830 ab7ef6b8
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 30 deletions
include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_kloop_v1.hpp
View file @ d20c472f
...@@ -21,8 +21,6 @@ ...@@ -21,8 +21,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_kloop_v2.hpp
View file @ d20c472f
...@@ -20,8 +20,6 @@ ...@@ -20,8 +20,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_light_v1.hpp
View file @ d20c472f
...@@ -10,7 +10,6 @@ ...@@ -10,7 +10,6 @@
#include "ck/utility/philox_rand.hpp" #include "ck/utility/philox_rand.hpp"
#include "ck/tensor_description/tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "ck/tensor_description/tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
// #include "ck/tensor_operation/gpu/device/device_batched_multihead_attention_backward.hpp" // TODO
#include "ck/tensor_operation/gpu/device/device_base.hpp" #include "ck/tensor_operation/gpu/device/device_base.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp" #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/masking_specialization.hpp" #include "ck/tensor_operation/gpu/device/masking_specialization.hpp"
...@@ -22,8 +21,6 @@ ...@@ -22,8 +21,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_light_v2.hpp
View file @ d20c472f
...@@ -21,8 +21,6 @@ ...@@ -21,8 +21,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_v1.hpp
View file @ d20c472f
...@@ -10,7 +10,6 @@ ...@@ -10,7 +10,6 @@
#include "ck/utility/philox_rand.hpp" #include "ck/utility/philox_rand.hpp"
#include "ck/tensor_description/tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "ck/tensor_description/tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
// #include "ck/tensor_operation/gpu/device/device_batched_multihead_attention_backward.hpp" // TODO
#include "ck/tensor_operation/gpu/device/device_base.hpp" #include "ck/tensor_operation/gpu/device/device_base.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp" #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/masking_specialization.hpp" #include "ck/tensor_operation/gpu/device/masking_specialization.hpp"
...@@ -21,8 +20,6 @@ ...@@ -21,8 +20,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_v2.hpp
View file @ d20c472f
...@@ -20,8 +20,6 @@ ...@@ -20,8 +20,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp
View file @ d20c472f
...@@ -22,7 +22,6 @@ ...@@ -22,7 +22,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/host_utility/io.hpp" #include "ck/host_utility/io.hpp"
#include "ck/library/utility/numeric.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
......
include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_kloop_v1.hpp
View file @ d20c472f
...@@ -10,7 +10,6 @@ ...@@ -10,7 +10,6 @@
#include "ck/utility/philox_rand.hpp" #include "ck/utility/philox_rand.hpp"
#include "ck/tensor_description/tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "ck/tensor_description/tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
// #include "ck/tensor_operation/gpu/device/device_batched_multihead_attention_backward.hpp" // TODO
#include "ck/tensor_operation/gpu/device/device_base.hpp" #include "ck/tensor_operation/gpu/device/device_base.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp" #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/masking_specialization.hpp" #include "ck/tensor_operation/gpu/device/masking_specialization.hpp"
...@@ -21,8 +20,6 @@ ...@@ -21,8 +20,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_kloop_v2.hpp
View file @ d20c472f
...@@ -10,7 +10,6 @@ ...@@ -10,7 +10,6 @@
#include "ck/utility/philox_rand.hpp" #include "ck/utility/philox_rand.hpp"
#include "ck/tensor_description/tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "ck/tensor_description/tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
// #include "ck/tensor_operation/gpu/device/device_batched_multihead_attention_backward.hpp" // TODO
#include "ck/tensor_operation/gpu/device/device_base.hpp" #include "ck/tensor_operation/gpu/device/device_base.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp" #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/masking_specialization.hpp" #include "ck/tensor_operation/gpu/device/masking_specialization.hpp"
...@@ -21,8 +20,6 @@ ...@@ -21,8 +20,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_qloop_light_v1.hpp
View file @ d20c472f
...@@ -22,8 +22,6 @@ ...@@ -22,8 +22,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_qloop_light_v2.hpp
View file @ d20c472f
...@@ -10,7 +10,6 @@ ...@@ -10,7 +10,6 @@
#include "ck/utility/philox_rand.hpp" #include "ck/utility/philox_rand.hpp"
#include "ck/tensor_description/tensor_descriptor.hpp" #include "ck/tensor_description/tensor_descriptor.hpp"
#include "ck/tensor_description/tensor_descriptor_helper.hpp" #include "ck/tensor_description/tensor_descriptor_helper.hpp"
// #include "ck/tensor_operation/gpu/device/device_batched_multihead_attention_backward.hpp" // TODO
#include "ck/tensor_operation/gpu/device/device_base.hpp" #include "ck/tensor_operation/gpu/device/device_base.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp" #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/masking_specialization.hpp" #include "ck/tensor_operation/gpu/device/masking_specialization.hpp"
...@@ -22,8 +21,6 @@ ...@@ -22,8 +21,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_qloop_v1.hpp
View file @ d20c472f
...@@ -21,8 +21,6 @@ ...@@ -21,8 +21,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_qloop_v2.hpp
View file @ d20c472f
...@@ -21,8 +21,6 @@ ...@@ -21,8 +21,6 @@
#include "ck/host_utility/device_prop.hpp" #include "ck/host_utility/device_prop.hpp"
#include "ck/host_utility/kernel_launch.hpp" #include "ck/host_utility/kernel_launch.hpp"
#include "ck/library/utility/host_tensor.hpp"
namespace ck { namespace ck {
namespace tensor_operation { namespace tensor_operation {
namespace device { namespace device {
......
library/include/ck/library/utility/fill.hpp
View file @ d20c472f
...@@ -10,6 +10,7 @@ ...@@ -10,6 +10,7 @@
#include <type_traits> #include <type_traits>
#include <utility> #include <utility>
#include "ck/utility/type_convert.hpp"
#include "ck/utility/data_type.hpp" #include "ck/utility/data_type.hpp"
namespace ck { namespace ck {
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment