saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-18 21:21:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/tools/ci_build
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
..
github Integrate TensorRT into GPU Python package (#9785) 2021-11-18 13:26:51 -08:00
__init__.py
amd_hipify.py Decoder Attention CUDA Op (#9792) 2021-11-19 19:25:36 -08:00
build.py Integrate TensorRT into GPU Python package (#9785) 2021-11-18 13:26:51 -08:00
clean_docker_image_cache.py Sync ORTModule branch with master and fix tests (#6526) 2021-02-02 08:59:56 -08:00
coverage.py Sync ORTModule branch with master and fix tests (#6526) 2021-02-02 08:59:56 -08:00
gen_def.py Minimize changes to fix missing symbols used from C# (#8867) 2021-08-28 07:10:14 +10:00
get_docker_image.py Sync ORTModule branch with master and fix tests (#6526) 2021-02-02 08:59:56 -08:00
logger.py
op_registration_utils.py Remove Featurizers code (#9300) 2021-10-20 10:20:35 -07:00
op_registration_validator.py Support specifying globally allowed types from build script (#6677) 2021-02-22 14:05:00 -08:00
reduce_op_kernels.py Support required types when excluding typed registrations (#6871) 2021-03-08 08:22:07 -08:00
requirements.txt Restore transformers tests and disable some tests (#8530) 2021-07-29 14:09:36 -07:00
upload_python_package_to_azure_storage.py do not add pkg wheel entry to the index html file if it already exists (#9004) 2021-09-09 16:20:19 -07:00