### Description
Python code block on home page contained typo
Previous: outputs = session.run(None {"input": inputTensor})
Correction: outputs = session.run(None, {"input": inputTensor})
Fixes issue #21146
### 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. -->
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>
### Description
<!-- Describe your changes. -->
### 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. -->
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>
ACPT docs should be nested inside Ecosystem category in the docs
sidebar, but they currently show up outside of the category at the top
of the sidebar.
Need to add parent to address this issue.
### Description
<!-- Describe your changes. -->
### 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. -->
Adding to the docs a link on how to embed an externally compiled engine
and also mention that in case of an embedded engine the builder resource
is not needed.
### Description
Add an ACPT landing page to the ORT docs to publish supported
configurations + most recent releases
### 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. -->
### Description
Fix broken links referenced in issue #20790
Llama2 blog link was updated to the correct location and ResNet sample
was removed entirely because it no longer exists anywhere in the AML
docs
### 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. -->
Add a section for how to use three major TRT EP caches: TRT timing
cache, TRT engine cache and Embedded engine model /EPContext model.
Some materials are from my GTC slides.
update cudnn to 8.9.2.26 (Linux)<br/>8.9.2.26 (Windows)
### Description
<!-- Describe your changes. -->
### 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. -->
### Description
Fix package name
from ```dotnet add package Microsoft.ML.OnnxRuntimeGenAI.*Cuda*
--prerelease``` to ```dotnet add package
Microsoft.ML.OnnxRuntimeGenAI.DirectML --prerelease``` in DirectML
section.
### Motivation and Context
Clearly confusing for beginners if not fixed (will break further processes)
### Description
Update compatibility/version info for ORT 1.18 release
### 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. -->
### Description
<!-- Describe your changes. -->
### 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. -->
### Description
-These changes reflect the latest changes we have made to enable NPU
-Export OpenVINO Blob to ONNX Operator
-Enable QDQ Optimizations Passes
- Separate Device/Precision
### Motivation and Context
These changes reflect the latest changes we have made to enable NPU.
These changes reflect the latest changes we have made to enable rel-1.18
- If it fixes an open issue, please link to the issue here. -->
---------
Co-authored-by: Preetha Veeramalai <preetha.veeramalai@intel.com>
### Description
<!-- Describe your changes. -->
* Update TRT version to 10.0
### 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. -->
### Description
with-python.md does not currently include installation instructions for
CUDA 12.X, so I added the instructions from
https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements.
### 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. -->
### Description
File previously included TOC placeholder instead of actual TOC
### 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. -->
### Description
CUDA-ExecutionProvider.md table of contents previously not showing up
correctly b/c of spacing issue.
### 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. -->
Update the document for PR: Enable Cross-Compiling Support for ONNX
Runtime on Linux for RISC-V 64-bit.
https://github.com/microsoft/onnxruntime/pull/19238
Signed-off-by: Phoebe Chen <phoebe.chen@sifive.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
This PR update docs of Ascend CANN excution provider doc for #20075
### Changes
1. Add new option
`dump_om_model`: Whether to dump the OM(Offlined Model for Aasend Npu)
to disk
---------
Co-authored-by: Tianlei Wu <tlwu@microsoft.com>
### Description
<!-- Describe your changes. -->
### 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. -->
