lp:~yeonykim2/sandbox-yeonykim2/+git/trunk

Author: Suyeon Kim
Author Date: 2024-02-13 00:10:10 UTC

[debian/packaging] add initial debian packaing files.

- add related debian packging files.

Change-Id: Ic44b6fa397005249caa89b1015558c09ea839145
Signed-off-by: Suyeon Kim <suyeon5.kim@samsung.com>

Author: Adrian Lizarraga
Author Date: 2024-01-31 01:19:08 UTC

[Quant tool] Ensure MSFT opset for Q/DQ models (#19335)

### Description
Updates qdq quantization to ensure the final model has the
`com.microsoft` opset import if the model uses Q/DQ ops with the
`com.microsoft` domain (e.g., for int16 quantization)

### Motivation and Context
Need to ensure the MSFT domain is correctly set for all relevant cases.
Otherwise, shape inferencing tools will raise an exception.

Author: Suyeon Kim
Author Date: 2024-01-16 05:21:53 UTC

[Tizen/onnxruntime] Modified spec, patch and tar.gz files

modified spec, patch and tar.gz file for flatbuffer warning about implicit-fallthrough errors.

Change-Id: I73364a4083adb9252d53b3ec77a748e423079586
Signed-off-by: Suyeon Kim <suyeon5.kim@samsung.com>

Author: SuYeon
Author Date: 2023-12-04 00:46:38 UTC

[Add] Add patch files for packaging

Signed-off-by: SuYeon <suyeon5.kim@samsung.com>

Author: Tianlei Wu
Author Date: 2023-11-18 04:58:21 UTC

Cherry pick SDXL demo update to 1.16.3 (#18496)

Cherry pick SDXL demo update to 1.16.3

-----
Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>

Author: SuYeon
Author Date: 2023-11-10 04:48:08 UTC

[add] add wget repository url source path

Add tar.gz

Signed-off-by: SuYeon <suyeon5.kim@samsung.com>

Author: Changming Sun
Author Date: 2023-09-18 22:03:48 UTC

Cherry-picks pipeline changes to 1.16.0 release branch (#17577)

### Description
1. Delete Prefast tasks (#17522)
2. Disable yum update (#17551)
3. Avoid calling patchelf (#17365 and #17562) we that we can validate
the above fix

The main problem I'm trying to solve is: our GPU package depends on both
CUDA 11.x and CUDA 12.x . However, it's not easy to see the information
because ldd doesn't work with the shared libraries we generate(see issue
#9754) . So the patchelf change are useful for me to validate the
"Disabling yum update" was successful. As you can see we call "yum
update" from multiple places. Without some kind of validation it's hard
to say if I have covered all of them.
The Prefast change is needed because I'm going to update the VM images
in the next a few weeks. In case of we need to publish a patch release
after that.

### Motivation and Context
Without this fix we will mix using CUDA 11.x and CUDA 12.x. And it will
crash every time when we use TensorRT.