Merge remote-tracking branch 'origin/develop' into migx-flash-attn

4100d1d8 · Alan Turner · 48717006 · c8a8385f · 4100d1d8 · 48717006
Commit 4100d1d8 authored Aug 23, 2023 by Alan Turner
20 changed files
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f16_f16_instance_rank4_reduce4.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce1.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce2.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank3_reduce3.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce1.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce1.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce1.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce2.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce2.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce3.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce3.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce1.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce1.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce2.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce2.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce3.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce3.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce4.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce4.cpp
--- a/library/src/utility/device_memory.cpp
+++ b/library/src/utility/device_memory.cpp
--- a/profiler/README.md
+++ b/profiler/README.md
--- a/profiler/include/profiler/profile_gemm_splitk_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_splitk_impl.hpp