Tianlei Wu 0bb4ea6797 Update BiasGelu fusion and related ops (#23518) ... ### Description (1) Update BiasGelu fusion to support onnx Gelu-20 Since onnx Gelu-20 supports float/double/bf16/fp16, here we update related ops to support these data types in CUDA and ROCm execution providers: (2) Add double support for Gelu/FastGelu op in CUDA/ROCm execution provider (3) Add BFloat16 support for Gelu ops in CUDA execution provider (4) Add unit tests (5) Update operator documents ### Motivation and Context https://github.com/microsoft/onnxruntime/issues/23491		2025-01-30 22:53:59 -08:00
..
contrib_ops	Update BiasGelu fusion and related ops (#23518)	2025-01-30 22:53:59 -08:00
dml_ops
extended_graph_edge.h
function.cc
function_container.h
function_impl.h
function_inliner.h
function_template.h	Use onnx_protobuf.h to suppress some GCC warnings (#23453)	2025-01-21 20:25:12 -08:00
function_utils.cc
function_utils.h
graph.cc	Enable Ep context with external data for CPU nodes (#23498)	2025-01-28 20:22:22 -08:00
graph_flatbuffers_utils.cc
graph_flatbuffers_utils.h
graph_proto_serializer.cc
graph_proto_serializer.h
graph_utils.cc	Address CodeQL security issues on comparison of different types (#23276)	2025-01-07 17:30:44 -08:00
graph_utils.h
graph_viewer.cc
model.cc	Implement pre-packed blobs serialization on disk and their memory mapping on load (#23069)	2024-12-20 10:49:08 -08:00
model.h	Implement pre-packed blobs serialization on disk and their memory mapping on load (#23069)	2024-12-20 10:49:08 -08:00
model_load_utils.h
node_attr_utils.cc
node_attr_utils.h
op.cc
op.h
op_identifier.h
op_identifier_utils.cc
op_identifier_utils.h
ort_format_load_options.h
record.h
runtime_optimization_record.h
runtime_optimization_record_container.cc
runtime_optimization_record_container.h
schema_registry.cc