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
..
ci_build	Decoder Attention CUDA Op (#9792)	2021-11-19 19:25:36 -08:00
doc	Add graphviz into Dockerfile images for Python API documentation (#7819)	2021-06-02 16:12:54 -07:00
nuget	Enable building winml with --build_nuget (#9632)	2021-11-04 00:42:51 -07:00
perf_util	Update mysql-connector-java (#5802)	2020-11-16 14:09:14 -08:00
python	Update mobile prebuilt package ops to add support for opset 14 and 15 (#9717)	2021-11-18 10:44:39 +10:00