saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-28 20:11:22 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/onnxruntime/core/graph
History
Ye Wang 6856619b18
Decoder Attention CUDA Op (#9792) 
* add kernel interface

* register kernel

* add self/cross qkv projection without cache

* add LaunchTransQkv2 for (S,B,X,N,H) -> (X,B,N,S,H)

* refactor ConcatPastToPresent

* DecoderQkvToContext interface

* q,k,v buffer and cache as output

* qk, pv and transctx

* fix compiler error on linux machine

* key_padding_mask

* add test_parity file. However not runnable

* add partial unittest

* made partial attributes to inputs

* --gen_doc

* change kernel interface, add more tests

* morre parity tests

* fix test

* fix typo

* transpose optimizer has bug. remove it temporarily

* add input shape checks

* add type/shape inference

* fix cache shape check

* fix rocm build failure

* fix rocm build error

* review comments

* review comments
2021-11-19 19:25:36 -08:00
..
contrib_ops Decoder Attention CUDA Op (#9792) 2021-11-19 19:25:36 -08:00
dml_ops Update C++ Standard from 14 to 17 (#8041) 2021-06-25 14:08:01 -07:00
signal_ops Ensure ms-experimental domain Audio Ops build in mac pipeline (#8857) 2021-09-15 10:59:32 -07:00
function.cc Fixing bugs in ORT_NO_EXCEPTIONS (#9479) 2021-10-26 10:50:32 -07:00
function_container.h
function_impl.h add model local function support (#8540) 2021-09-08 11:47:01 -07:00
function_inliner.h
graph.cc Improve print functions for NodeArg, Node, and Graph (#9801) 2021-11-19 09:48:27 -08:00
graph_flatbuffers_utils.cc Remove experimental from ORT format namespace (#9729) 2021-11-11 19:46:30 -08:00
graph_flatbuffers_utils.h Remove experimental from ORT format namespace (#9729) 2021-11-11 19:46:30 -08:00
graph_utils.cc Enable selector action transformer infrastructure in minimal build. (#8804) 2021-08-27 17:16:05 +10:00
graph_utils.h Enable selector action transformer infrastructure in minimal build. (#8804) 2021-08-27 17:16:05 +10:00
graph_viewer.cc Add QDQ::Selector::Select to use const GraphViewer instead of mutable Graph (#9621) 2021-11-08 21:36:29 -08:00
model.cc Remove experimental from ORT format namespace (#9729) 2021-11-11 19:46:30 -08:00
model.h Remove experimental from ORT format namespace (#9729) 2021-11-11 19:46:30 -08:00
model_load_utils.h add model local function support (#8540) 2021-09-08 11:47:01 -07:00
onnx_protobuf.h Update C++ Standard from 14 to 17 (#8041) 2021-06-25 14:08:01 -07:00
op.cc
op.h Update C++ Standard from 14 to 17 (#8041) 2021-06-25 14:08:01 -07:00
record.h
runtime_optimization_record.h Add QDQ::Selector::Select to use const GraphViewer instead of mutable Graph (#9621) 2021-11-08 21:36:29 -08:00
runtime_optimization_record_container.cc Remove experimental from ORT format namespace (#9729) 2021-11-11 19:46:30 -08:00
runtime_optimization_record_container.h Disable partial runtime optimization implementation by default (#9748) 2021-11-12 17:37:29 -08:00
schema_registry.cc