saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-14 20:48:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/cmake/onnxruntime_optimizer.cmake
pengwa 8a98874e7e
Flash attention recompute (#20603) 
### Flash attn recompute

1. Allow PythonOp(FlashAttn) can be recomputed correctly.
45879ff5c2
2. Use JSON to pass the selected-to-recompute subgraphs.
3c374da678

#### Better Memory Efficiency 

Customer model can run both PyTorch SPDA and Flash Attn, this PR make it
possible to let the Flash Attn path work with ORTModule layerwise
recompute. The peak drop from 45.xGB to 32.xGB if we only compare the
layers (not including other pieces, BTW there are few more optimization
targeting other pieces as well later).

#### Better Perf

Using Flash ATTN bring additionally 16% end to end time reduction, with
highly aligned loss curve.


![image](https://github.com/microsoft/onnxruntime/assets/10530022/bb63894a-f281-49bc-a8e6-ff818439be38)

#### Use JSON File to pass Recompute Plans

To overcome the limitation of max length of the strings defined in
session options.

### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2024-05-21 13:38:19 +08:00

139 lines
8 KiB
CMake
Raw Blame History

# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
set(onnxruntime_optimizer_src_patterns)
if (onnxruntime_MINIMAL_BUILD)
# we include a couple of files so a library is produced and we minimize other changes to the build setup.
# if the transformer base class is unused it will be excluded from the final binary size
list(APPEND onnxruntime_optimizer_src_patterns
"${ONNXRUNTIME_INCLUDE_DIR}/core/optimizer/graph_transformer.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/graph_transformer.cc"
)
if (onnxruntime_EXTENDED_MINIMAL_BUILD)
list(APPEND onnxruntime_optimizer_src_patterns
"${ONNXRUNTIME_INCLUDE_DIR}/core/optimizer/graph_transformer_utils.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/conv_activation_fusion.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/conv_activation_fusion.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/graph_transformer_utils.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/initializer.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/initializer.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/matmul_nbits_fusion.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/matmul_nbits_fusion.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/nhwc_transformer.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/nhwc_transformer.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/qdq_final_cleanup.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/qdq_final_cleanup.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/qdq_util.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/qdq_util.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/qdq_actions.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/qdq_actions.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/qdq_selector_action_transformer.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/qdq_selector_action_transformer.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/qdq_selectors.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/qdq_selectors.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/shared/utils.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/shared/utils.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/actions.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/actions.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/helpers.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/helpers.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/helpers.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/helpers.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/selector_action_transformer_apply_contexts.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/selector_action_transformer.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/selector_action_transformer.h"
# files required for layout transformation
"${ONNXRUNTIME_ROOT}/core/optimizer/layout_transformation/layout_transformation.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/layout_transformation/layout_transformation.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/layout_transformation/layout_transformation_potentially_added_ops.h"
# files required for transpose optimization post-layout transformation
"${ONNXRUNTIME_ROOT}/core/optimizer/transpose_optimization/optimizer_api.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/transpose_optimization/onnx_transpose_optimization.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/transpose_optimization/onnx_transpose_optimization.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/transpose_optimization/ort_optimizer_api_impl.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/transpose_optimization/ort_optimizer_utils.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/transpose_optimization/ort_transpose_optimization.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/transpose_optimization/ort_transpose_optimization.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/utils.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/utils.h"
)
endif()
else()
list(APPEND onnxruntime_optimizer_src_patterns
"${ONNXRUNTIME_INCLUDE_DIR}/core/optimizer/*.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/*.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/*.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/compute_optimizer/*.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/compute_optimizer/*.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/layout_transformation/*.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/layout_transformation/*.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/*.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/*.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/*.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/*.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/shared/utils.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/qdq_transformer/selectors_actions/shared/utils.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/*.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/selectors_actions/*.cc"
"${ONNXRUNTIME_ROOT}/core/optimizer/transpose_optimization/*.h"
"${ONNXRUNTIME_ROOT}/core/optimizer/transpose_optimization/*.cc"
)
endif()
if (onnxruntime_ENABLE_TRAINING)
list(APPEND onnxruntime_optimizer_src_patterns
"${ORTTRAINING_SOURCE_DIR}/core/optimizer/*.h"
"${ORTTRAINING_SOURCE_DIR}/core/optimizer/*.cc"
"${ORTTRAINING_SOURCE_DIR}/core/optimizer/compute_optimizer/*.h"
"${ORTTRAINING_SOURCE_DIR}/core/optimizer/compute_optimizer/*.cc"
"${ORTTRAINING_SOURCE_DIR}/core/optimizer/memory_optimizer/*.h"
"${ORTTRAINING_SOURCE_DIR}/core/optimizer/memory_optimizer/*.cc"
)
endif()
file(GLOB onnxruntime_optimizer_srcs CONFIGURE_DEPENDS ${onnxruntime_optimizer_src_patterns})
source_group(TREE ${REPO_ROOT} FILES ${onnxruntime_optimizer_srcs})
if (onnxruntime_EXTERNAL_TRANSFORMER_SRC_PATH)
set(onnxruntime_external_transformer_src_patterns)
list(APPEND onnxruntime_external_transformer_src_patterns
"${onnxruntime_EXTERNAL_TRANSFORMER_SRC_PATH}/*.cc"
"${onnxruntime_EXTERNAL_TRANSFORMER_SRC_PATH}/*.cpp"
)
file(GLOB onnxruntime_external_transformer_src ${onnxruntime_external_transformer_src_patterns})
list(APPEND onnxruntime_optimizer_srcs ${onnxruntime_external_transformer_src})
endif()
onnxruntime_add_static_library(onnxruntime_optimizer ${onnxruntime_optimizer_srcs})
onnxruntime_add_include_to_target(onnxruntime_optimizer onnxruntime_common onnxruntime_framework onnx onnx_proto ${PROTOBUF_LIB} flatbuffers::flatbuffers Boost::mp11 safeint_interface)
target_include_directories(onnxruntime_optimizer PRIVATE ${ONNXRUNTIME_ROOT})
if (onnxruntime_ENABLE_TRAINING)
target_include_directories(onnxruntime_optimizer PRIVATE ${ORTTRAINING_ROOT})
onnxruntime_add_include_to_target(onnxruntime_optimizer nlohmann_json::nlohmann_json)
if (onnxruntime_ENABLE_TRAINING_TORCH_INTEROP)
onnxruntime_add_include_to_target(onnxruntime_optimizer Python::Module)
endif()
endif()
if (onnxruntime_ENABLE_TRITON)
target_link_libraries(onnxruntime_optimizer PRIVATE nlohmann_json::nlohmann_json)
onnxruntime_add_include_to_target(onnxruntime_optimizer Python::Module)
endif()
add_dependencies(onnxruntime_optimizer ${onnxruntime_EXTERNAL_DEPENDENCIES})
set_target_properties(onnxruntime_optimizer PROPERTIES FOLDER "ONNXRuntime")
if (NOT onnxruntime_BUILD_SHARED_LIB)
install(DIRECTORY ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/optimizer DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/core)
install(TARGETS onnxruntime_optimizer
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
FRAMEWORK DESTINATION ${CMAKE_INSTALL_BINDIR})
endif()
if (onnxruntime_USE_ROCM)
add_dependencies(onnxruntime_optimizer generate_hipified_files)
endif()
Reference in a new issue View git blame Copy permalink