saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-13 18:08:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/onnxruntime/python
History
Young Jin Kim e9057d2e49
ZCode FastFormers changes (#5827) 
* Add FBGEMM submodule

* Add fbgemm based per-channel quantization

* Add missing logic for pre-layernorm transformer model fusion

* add support for structured pruning architecture -fastformers

* Fix windows build

* Add a default behavior when head_size is not present for the backward compatibility

* Remove FBGEMM and default to tensor-wise quantization, column-wise quantization will be enabled later

* Fixed some unit test errors

* Fix windows compile error and unit test errors

* delete the option removed from the upstream

* Addresses review comments and fixes a merge error

* Remove commented out code

* add non-zero zp support

* support A and B scale with any dimensions

* fix build breaks

* fix warning in MSVC

* Fix bug for not checking original float value names when treat it as not existing.

* Clean up head size

* Clean up python tools

* Enable per column quantization

* fix quant weight cleanup bug

* A few code clean up

* Some code clean-up

* Some code clean-up

* Change option name

* update default value

* Rename option and parameter names

* Missing argument name change

* Add tests for quantization options for attention and matmul

Co-authored-by: Yufeng Li <liyufeng1987@gmail.com>
Co-authored-by: Lei Zhang <zhang.huanning@hotmail.com>
2021-05-17 21:12:21 -07:00
..
backend fix py packaging pipeline (#5038) 2020-09-03 09:32:10 -07:00
datasets replace invalid sample (#4567) 2020-07-21 23:51:17 -07:00
tools ZCode FastFormers changes (#5827) 2021-05-17 21:12:21 -07:00
training Enable running PEP8 on python scripts using flake8 (#3928) 2020-05-15 07:15:06 +10:00
__init__.py Enable running PEP8 on python scripts using flake8 (#3928) 2020-05-15 07:15:06 +10:00
_ld_preload.py Enable running PEP8 on python scripts using flake8 (#3928) 2020-05-15 07:15:06 +10:00
_pybind_state.py Add cupti path for python gpu packaging pipeline (#7200) 2021-04-02 12:12:46 -07:00
exported_symbols.lst
onnxruntime_collect_build_info.py Liqun/ort training version (#7620) 2021-05-14 09:54:19 -07:00
onnxruntime_inference_collection.py support loading external execution provider from python frontend (#7332) 2021-04-23 09:54:09 -07:00
onnxruntime_pybind_exceptions.h
onnxruntime_pybind_mlvalue.cc Change onnxruntime::make_unique to std::make_unique (#7502) 2021-04-29 17:04:53 -07:00
onnxruntime_pybind_mlvalue.h Support sharing of initializers between session via the Python API (#5407) 2020-10-09 20:26:28 -07:00
onnxruntime_pybind_state.cc Add more TensorRT env variables to provider options (#7698) 2021-05-16 22:09:52 -07:00
onnxruntime_pybind_state_common.cc Enable passing initial optimizer state while creating training session (#5869) 2020-12-08 21:20:51 -05:00
onnxruntime_pybind_state_common.h Change onnxruntime::make_unique to std::make_unique (#7502) 2021-04-29 17:04:53 -07:00
onnxruntime_validation.py Liqun/ort training version (#7620) 2021-05-14 09:54:19 -07:00
pybind.def
version_script.lds