ort-customops/onnxruntime_extensions
Wenbing Li aa2c82fa67
Add the MLlama Imaging Processing Support (#823)
* initial checkins for mllama image process

* fix some tests

* some fixings

* add more image

* More test assertions

* parity test passed

* code clean up

* code refinement
2024-10-22 14:24:09 -07:00
..
onnxprocess Compatible with onnxruntime-gpu package (#410) 2023-04-26 17:17:23 -07:00
pnp Fix the unit test failure with ONNX 1.14 package. (#428) 2023-05-08 11:37:54 -07:00
tools Add support for YOLO v8 Pose post-processing. (#605) 2023-12-20 08:51:29 +10:00
__init__.py sync to flash attention kernel 2.5.9 and add document of how to write custom op (#757) 2024-07-10 07:09:40 -07:00
_cuops.py Unify the spm/bpe tokenizers (#666) 2024-03-06 10:07:05 -08:00
_extensions_pydll.pyi add a gen_processing_model option to cast token-id for int64 (#632) 2024-01-12 10:15:18 -08:00
_hf_cvt.py Optimize the tokenizer for efficiency (#797) 2024-08-27 18:57:50 -07:00
_ocos.py make onnx package to be optional. (#653) 2024-02-15 14:09:04 -08:00
_ortapi2.py make onnx package to be optional. (#653) 2024-02-15 14:09:04 -08:00
_torch_cvt.py Feature extraction C API for whipser model (#755) 2024-07-11 11:20:36 -07:00
cmd.py Add a new API for building data processing graph from Huggingface transformers processor/tokenizer (#482) 2023-07-17 16:50:58 -07:00
cvt.py add a gen_processing_model option to cast token-id for int64 (#632) 2024-01-12 10:15:18 -08:00
pp_api.py Add the MLlama Imaging Processing Support (#823) 2024-10-22 14:24:09 -07:00
util.py add a gen_processing_model option to cast token-id for int64 (#632) 2024-01-12 10:15:18 -08:00