onnxruntime/onnxruntime
Scott McKay 56bd96a3f5
Incrementally free initializers while saving to OrtValue instances (#12485)
* Free initializer TensorProto instances as they're converted to OrtValue to reduce peak memory usage.

Co-authored-by: Pranav Sharma <prs@microsoft.com>
2022-08-09 10:59:10 +10:00
..
contrib_ops Fix various warning in kernel explorer (#12501) 2022-08-08 11:15:41 -07:00
core Incrementally free initializers while saving to OrtValue instances (#12485) 2022-08-09 10:59:10 +10:00
gsl
python new quantized operators split (#12495) 2022-08-08 15:12:09 -04:00
test new quantized operators split (#12495) 2022-08-08 15:12:09 -04:00
tool/etw
wasm EP factory creation cleanup and enhancements. (#11798) 2022-06-16 07:01:41 +10:00
__init__.py Bump ort version number (#11948) 2022-07-22 12:55:53 -07:00
ReformatSource.ps1
ReformatSourcePython.bat Add python docstring linting in vscode settings (#11316) 2022-04-23 06:23:04 -07:00
VSCodeCoverage.runsettings