onnxruntime/onnxruntime
Dmitri Smirnov 87e8a5dfa8
Implement DML copy for Lora Adapters (#22396)
### Description
Request and create DML EP and its data transfer.
Use to copy on device.

The PR includes changes to fix issues in DML provider.

### Motivation and Context
This enables Lora users to run it with DML which is important for GenAI.

Co-authored-by: @PatriceVignola

---------

Co-authored-by: Patrice Vignola <vignola.patrice@gmail.com>
2024-10-14 12:26:50 -07:00
..
contrib_ops DecoderMaskedMultiHeadAttention CPU kernel. (#22292) 2024-10-12 13:43:00 -07:00
core Implement DML copy for Lora Adapters (#22396) 2024-10-14 12:26:50 -07:00
lora Accomodate BE platforms. Make sure we always write flatbuffers LE (#22375) 2024-10-11 09:14:44 -07:00
python Implement DML copy for Lora Adapters (#22396) 2024-10-14 12:26:50 -07:00
test Implement DML copy for Lora Adapters (#22396) 2024-10-14 12:26:50 -07:00
tool/etw
wasm [WebNN EP] Enable IO Bindings with MLTensor (#21301) 2024-09-27 17:24:21 -07:00
__init__.py Multi-Lora support (#22046) 2024-09-30 15:59:07 -07:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings