DRAFT PR until images and thumbnail are provided
---------
Co-authored-by: Scott McKay <Scott.McKay@microsoft.com>
Co-authored-by: Emma Ning <43255631+EmmaNingMS@users.noreply.github.com>
This documentation adds documentation on:
- how to allocate CUDA device tensors from C++ and python
- how to use DML device tensors from C++ and python
- it also shows how to leverage existing GPU allocations in ORT
- how to overlap PCI copies and GPU execution using CUDA streams
- how to overlap PCI copies and GPU execution using D3D12 Command Lists
and custom resources
---------
Co-authored-by: Tianlei Wu <tlwu@microsoft.com>
- doc suggests that QDQ model are created with dynamic quant, which is
not the case anymore.
- updating and restructuring the doc
### Description
<!-- Describe your changes. -->
- QDQ model format representation doesn't come for dynamic quantization,
but the doc was suggesting.
- May be a couple of years back this support was there but not anymore
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
- Clears misunderstanding that QDQ Onnx models can be created with
dynamic quantization.
https://github.com/microsoft/onnxruntime/issues/20125
### Description
Adding cookie consent for google analytics (Adobe WIP), daisyui4 changes
and updates, updates to events page, and added MD blog support (for
upcoming blogs).
Staged at: https://maanavd.github.io/onnxruntime/
---------
Co-authored-by: MaanavD <maanavdalal@microsoft.com>
### Description
Added docs for ONNX 1.17 covering logging, tracing, and QNN EP Profiling
### Motivation and Context
- ONNX Logging has not been documented
- ONNX Tracing with Windows has barely been documented
- ONNX 1.17 has new tracing and QNN EP Profiling
PRs: #16259, #18201, #18882, #19397
Command was split from `shape_inference.py` to address import sequence
warnings in 8004db4bf1 and was not
updated.
Anyone following the docs prior to this change would have encountered;
```
root@Raze:~# python -m onnxruntime.quantization.shape_inference --help
/usr/lib/python3.10/runpy.py:126: RuntimeWarning: 'onnxruntime.quantization.shape_inference' found in sys.modules after import of package 'onnxruntime.quantization', but prior to execution of 'onnxruntime.quantization.shape_inference'; this may result in unpredictable behaviour
warn(RuntimeWarning(msg))
```
Instead of the expected;
```
root@Raze:~# ./onnxtesting/bin/python -m onnxruntime.quantization.preprocess --help
usage: preprocess.py [-h] --input INPUT --output OUTPUT [--skip_optimization SKIP_OPTIMIZATION] [--skip_onnx_shape SKIP_ONNX_SHAPE]
[--skip_symbolic_shape SKIP_SYMBOLIC_SHAPE] [--auto_merge] [--int_max INT_MAX] [--guess_output_rank]
[--verbose VERBOSE] [--save_as_external_data] [--all_tensors_to_one_file]
[--external_data_location EXTERNAL_DATA_LOCATION]
[--external_data_size_threshold EXTERNAL_DATA_SIZE_THRESHOLD]
Model optimizer and shape inferencer[continues]
```
### Description
-WPA OSS plugins
-Pertetto UI which is recommended by Google over deprecated
chrome://tracing experience
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- I tried both chrome://tracing and Perfetto to open the .json and it's
not a great expreince. If on Windows, WPA is a MUCH better experience
and easier to work with the data/report. Also Google recommends Perfetto
vs chrome://tracing so updated that as well
### Description
revise example C++ code of using file path.
normalize the example code to use macros `ORTCHAR_T` and `ORT_TSTR`
defined in onnxruntime_c_api.h so that the code works in both Windows
and UNIX.
This PR resolves#14859
* custom.md - use release tags
* Rename mobile performance tuning doc.
* Move old mobile performance tuning docs.
* remove title
* Adapt original documentation and add more for 1.11.
* Adjust doc ordering.
* Update version text.
* Update nav, fix links.
* rework docs
* Explain the usage of dynamic cost model
* add tool usage
* fix a few grammar
* refactor
* refactor
* refactor
* fixing comments
Co-authored-by: Randy Shuai <rashuai@microsoft.com>
[Enable proper mimalloc override](https://github.com/microsoft/onnxruntime/pull/9944) PR has fixed a number of issues with regards to building onnxruntime with mimalloc. This PR documents usage of mimalloc.
