onnxruntime/onnxruntime
Ankit Maheshkar 1f88284f96
OVEP 1.21.0 Development Updates (#23080)
### Description
OVEP development changes for ORT 1.21 Release
 
 
### Motivation and Context
- Has Critical Bug Fixes
- Improved Performance optimizations for both memory & inference latency
(https://github.com/intel/onnxruntime/pull/513)
- Enabled Model Compilation using NPUW
(https://github.com/intel/onnxruntime/pull/508)
- Fixed support for EPContext embed mode 0 for lower memory utilization
- Updated NuGet package name as `Intel.ML.OnnxRuntime.OpenVino`
- Fixed QDQ Stripping logic on NPU
2024-12-11 22:26:32 -08:00
..
contrib_ops Implement 2d tiled matmulnbits specialized for prefill (#23058) 2024-12-10 17:07:11 -08:00
core OVEP 1.21.0 Development Updates (#23080) 2024-12-11 22:26:32 -08:00
lora Accomodate BE platforms. Make sure we always write flatbuffers LE (#22375) 2024-10-11 09:14:44 -07:00
python [VSINPU]Split/Pad and some element-wise OPs support (#22916) 2024-12-02 13:57:30 -08:00
test disable the EP context embed model by default in session option (#23070) 2024-12-11 17:26:29 -08:00
tool/etw
wasm [WebNN] Fixed WebNN Module undefined issue (#22795) 2024-11-11 21:31:24 -08:00
__init__.py bumps up version in main from 1.20 -> 1.21 (#22482) 2024-10-17 12:32:35 -07:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings