onnxruntime/onnxruntime
Scott McKay 329fd03bb4
Add int32_t as required type to some operators (#7192)
* Updates to some operators to always support int32 and int64 based on testing of Android package build config with a minimal build.

If an operator can be used for shape manipulation (int64) it is frequently used for indices manipulation (int32), so we enable both types for that set of ops.
  - e.g. BERT models take indices as input
  - Scatter/Gather ops utilize indices

Misc. fix to python bindings to exclude call that fails in a minimal build.
2021-04-01 19:32:34 +10:00
..
contrib_ops pull onnx latest commit (#7102) 2021-03-29 11:00:38 -07:00
core Add int32_t as required type to some operators (#7192) 2021-04-01 19:32:34 +10:00
featurizers_ops/cpu Consolidate MLTypeCallDispatcher classes (#6651) 2021-02-12 13:26:56 -08:00
gsl
python Add int32_t as required type to some operators (#7192) 2021-04-01 19:32:34 +10:00
test Support int32 type for TopK CPU op (#7089) 2021-03-31 18:08:21 -07:00
tool/etw
.style.yapf
__init__.py Add robust dependency check for Python package (#6436) 2021-02-21 15:11:28 -08:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings