Ye Wang ef42fd09fb google/mt5 optimization and fix (#15454) ... ### Description <!-- Describe your changes. --> 1. enabled self-attention fusion in mt-5 decoder graph 2. fix a parity issue https://github.com/microsoft/onnxruntime/issues/15042 ### 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. --> --------- Co-authored-by: Ubuntu <wy@v100-2.0cdb2e52twzevn1i4fi45bylyg.jx.internal.cloudapp.net>		2023-04-11 00:09:11 -07:00
..
backend	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
datasets	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
providers/tvm	Enable pylint and numpy rules (#15218)	2023-03-27 20:37:53 -07:00
tools	google/mt5 optimization and fix (#15454)	2023-04-11 00:09:11 -07:00
torch_cpp_extensions	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
training
__init__.py
_ld_preload.py
_pybind_state.py.in
exported_symbols.lst
numpy_helper.h
onnxruntime_collect_build_info.py	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
onnxruntime_inference_collection.py	Add type annotations to onnxruntime_inference_collection.py (#15364)	2023-04-05 10:32:49 -07:00
onnxruntime_pybind.h
onnxruntime_pybind_exceptions.cc
onnxruntime_pybind_exceptions.h
onnxruntime_pybind_iobinding.cc
onnxruntime_pybind_mlvalue.cc	Enable Opset11 Sequence Ops on DirectML, and make the CPU implementations agnostic to backend EP (#14442)	2023-02-21 18:08:28 -08:00
onnxruntime_pybind_mlvalue.h
onnxruntime_pybind_module.cc	Add GetVersionSting API for C++, C# and Python (#14873)	2023-03-02 17:11:07 -08:00
onnxruntime_pybind_ortvalue.cc	Enable ORT in TorchDynamo (#13259)	2022-11-01 11:19:29 -07:00
onnxruntime_pybind_schema.cc	Pass SessionOptions to XnnpackProviderFactoryCreator. (#13318)	2022-12-10 14:23:46 +08:00
onnxruntime_pybind_sparse_tensor.cc	Multi-stream execution support (#13495)	2022-12-15 07:39:29 -08:00
onnxruntime_pybind_state.cc	Re-work global objects dependancies in pybind layer. (#14941)	2023-03-10 13:55:31 -08:00
onnxruntime_pybind_state.h
onnxruntime_pybind_state_common.cc	Allow CUDA EP enable or disable TunableOp via session options and environment variable (#13601)	2022-11-15 14:43:54 +08:00
onnxruntime_pybind_state_common.h	Re-work global objects dependancies in pybind layer. (#14941)	2023-03-10 13:55:31 -08:00
onnxruntime_validation.py	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
pybind.def
version_script.lds
version_script_expose_onnx_protobuf.lds