onnxruntime/onnxruntime
Zhang Lei b000ec91cc
Add quantization tool and its unittest with s8s8 support (#10007)
* Add quantization tool with s8s8 support
  * Add unittest for existing s8s8 support operators
  * Comment ready unittest for upcomming s8s8 operator (ConvInteger, and Resize)
  * Minor change on quantization tools

* Use different s8 min value upon weight or activation.

* use same qmin for reduce ranged s8.
2021-12-10 16:40:01 -08:00
..
contrib_ops add fallback of s8s8 support on x64 (#9995) 2021-12-10 11:33:19 -08:00
core add fallback of s8s8 support on x64 (#9995) 2021-12-10 11:33:19 -08:00
gsl Change TensorShape to typically not allocate heap memory (#9542) 2021-11-08 10:29:54 -08:00
python Add quantization tool and its unittest with s8s8 support (#10007) 2021-12-10 16:40:01 -08:00
test Add quantization tool and its unittest with s8s8 support (#10007) 2021-12-10 16:40:01 -08:00
tool/etw
wasm Merged PR 6524907: Fix merge conflicts from public ORT to WindowsAI ORT 2021-10-01 22:47:52 +00:00
.style.yapf
__init__.py Merged PR 6524907: Fix merge conflicts from public ORT to WindowsAI ORT 2021-10-01 22:47:52 +00:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings Merged PR 6622174: merge latest onnxruntime into dmldev 2021-10-30 19:59:33 +00:00