Commit graph

388 commits

Author SHA1 Message Date
Yifan Li
9c227d1432
Update jetson instruction (#18204)
### Description
* Update instruction based on latest jetpack 5.1.2+ORT 1.16
* Add instructions of installing CUDA 11.8/latest CMake
* Add tips of building ORT on jetson

Check
https://yf711.github.io/onnxruntime/docs/build/eps.html#nvidia-jetson-tx1tx2nanoxavier
for preview
2023-11-02 14:18:25 -07:00
Changming Sun
be3c14939f
Update Cross-compiling instructions (#18205) 2023-10-31 16:10:28 -07:00
George Wu
9bbb897822
[TensorRT EP] update link to TensorRT install instructions (#18167) 2023-10-30 11:07:53 -07:00
Jordan
126c35b202
Update quantization preprocessing command in docs (#18146)
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]
```
2023-10-30 09:12:34 -07:00
Preetha Veeramalai
2f66a5061e
Update documentation for OVEP Rel-1.16 (#18060)
### Description
Update OVEP Document for 5.1 release
2023-10-28 14:39:33 -07:00
Nat Kershaw (MSFT)
812874539c
Update CUDA dependencies for 1.16 (#18062) 2023-10-28 14:23:18 -07:00
Maanav Dalal
918f4aa1fa
Website revamp final (#17638)
Co-authored-by: MaanavD <maanavdalal@microsoft.com>
Co-authored-by: Prasanth Pulavarthi <prasanth.pulavarthi@microsoft.com>
Co-authored-by: Sophie Schoenmeyer <sschoenmeyer@microsoft.com>
Co-authored-by: sophies927 <107952697+sophies927@users.noreply.github.com>
Co-authored-by: Parinita Rahi <101819959+parinitarahi@users.noreply.github.com>
Co-authored-by: kshama-msft <66488860+kshama-msft@users.noreply.github.com>
2023-10-27 17:26:41 -07:00
Nat Kershaw (MSFT)
082ce696c0
Editorial pass of C# tutorial (#17704) 2023-10-11 17:27:04 -07:00
Nat Kershaw (MSFT)
d910f96f08
Update CoreML-ExecutionProvider.md (#17873) 2023-10-11 11:13:56 -07:00
Sayan Shaw
fb7a2e08fd
Add SentencePieceTokenizer and GPT2Tokenizer examples for Extensions Python converter API docs (#17708)
Co-authored-by: Sayan Shaw <sayanshaw@microsoft.com>
2023-10-05 15:37:09 -07:00
Arthur Kim
6b12dc5f6f
Python API has no AddConfigEntry and kOrtSessionOptionsConfigAllowIntraOpSpinning (#17712)
### Description
<!-- Describe your changes. -->


bcc6205161/include/onnxruntime/core/session/onnxruntime_session_options_config_keys.h (L94C74-L94C105)

### 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. -->


@ivberg
2023-09-26 23:33:46 -07:00
Dmitri Smirnov
f3fa223ee8
Update C# Pages in view of the new preferred inference API (#17642)
### Description
Re-work C# code samples with OrtValue API.
Bring `C# Tutorial: Basic` to index. 

The site is currently published
[here](https://yuslepukhin.github.io/onnxruntime)


### Motivation and Context
Direct all future usage to `Ortvalue` API
2023-09-26 10:35:20 -07:00
Scott McKay
acc1b8b5ea
Update some op docs for release (#17626)
### Description
<!-- Describe your changes. -->
Update some ops docs for 1.16 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. -->
2023-09-25 14:57:39 -07:00
ivberg
701728956e
Update ORT Performance threading docs (#16995) 2023-09-25 14:36:50 -07:00
Caroline Zhu
e0c98ce56b
[website] Updated ORT-training installation instructions (#17538)
### Description
Live preview [here](https://carzh.github.io/onnxruntime/).

* updates CUDA option in training to be a specific CUDA version
* updates with the now-preferred devops source for stable version for
1.16.0

### Motivation and Context
* updates installation command for stable ORT training
2023-09-21 15:13:08 -07:00
Vincent Wang
07eed73d94
Update Docs for rel-1.16.0 (#17588)
Update docs for release 1.16.0.
2023-09-21 09:01:31 -07:00
Faith Xu
cd20cac27f
[website] Fix sidebar ordering (#17620)
### Description
- Fixes ordering of EPs in sidebar
- Also fixes #17607 


### 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. -->
2023-09-20 14:11:50 -07:00
Nat Kershaw (MSFT)
ea25f19229
Fix broken OpenVINO link (#17579)
Co-authored-by: nakersha <natalie.kershaw@microsoft.com>
2023-09-18 16:56:59 -07:00
Nat Kershaw (MSFT)
19687c00ee
Fix custom op docs (#17571) 2023-09-15 19:20:10 -07:00
RandySheriffH
54ebb4ded7
Doc custom op lifetime (#17576) 2023-09-15 19:14:19 -07:00
Caroline Zhu
dc06ffedac
Add training artifacts to the ORT build for web docs (#17455)
### Description
Updates the ORT build for web documentation to include the training WASM
artifacts


### Motivation and Context
* We are adding training bindings for web
* [This PR](https://github.com/microsoft/onnxruntime/pull/16521)
extended the WASM API wrapper to include training, allowing for training
artifacts (`ort-training-wasm-simd.wasm` and
`ort-training-wasm-simd.js`) to be built, and was merged in last week
* [This PR](https://github.com/microsoft/onnxruntime/pull/17319) will
add the training artifacts to the web pipeline & updates the
pull-wasm-artifacts script to also pull training artifacts.

This PR should not be merged in until the [pipeline
PR](https://github.com/microsoft/onnxruntime/pull/17319) is merged.
2023-09-11 10:00:49 -07:00
Xavier Dupré
71d60b408a
Fix links to notebooks broken because the notebooks were moved (#17446) 2023-09-07 10:49:30 -07:00
Nat Kershaw (MSFT)
09f9e6d6fa
Test staging website from a branch (#17440) 2023-09-06 22:04:25 -07:00
Edward Chen
3963d364dc
Fix typo in sample code. (#17426) 2023-09-05 15:19:13 -07:00
Edward Chen
2cced52151
Add documentation for installing ORT Extensions on Android and iOS. (#17397)
### Description
<!-- Describe your changes. -->

Add documentation for installing ORT Extensions on Android and iOS.
Some other minor doc updates.

https://edgchen1.github.io/onnxruntime/docs/extensions/

### 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. -->

Documentation.
2023-09-05 11:39:36 -07:00
Nat Kershaw (MSFT)
ae98203d4c
Minor edits to extensions (#17396) 2023-09-01 16:30:53 -07:00
Sayan Shaw
cdba245a6e
Added initial ORT Extensions docs for onnxruntime website (#16723)
## Preview staged site
[here](https://sayanshaw24.github.io/onnxruntime/docs/extensions/).

**TODO**: In the future, make PR to add/update descriptions for the
following new/deprecated ops:

**NLP Ops**
- BlingFireSentenceBreaker
- BpeTokenizer

**String Ops**
- StringSplit
- StringUpper
- StringLower
- StringECMARegexSplitWithOffsets
- StringRaggedTensorToDense
- StringMapping

**Math Ops**
- Inverse
- NegPos
- SegmentExtraction
- SegmentSum

**Tensor Ops**
- RaggedTensorToSparse
- RaggedTensorToDense

---------

Co-authored-by: Sayan Shaw <sayanshaw@microsoft.com>
Co-authored-by: Nat Kershaw (MSFT) <nakersha@microsoft.com>
2023-09-01 15:56:33 -07:00
RandySheriffH
43da400aa6
Fix inner links (#17381) 2023-08-31 17:16:50 -07:00
RandySheriffH
73e0000190
Doc custom op lite (#17287)
Doc custom op lite for a few key improvements:

1. lite interface.
2. cuda & rocm support.
3. one op, varied data type.

---------

Co-authored-by: Randy Shuai <rashuai@microsoft.com>
2023-08-30 12:48:46 -07:00
RandySheriffH
e532835a3b
Document AzureEP 1.16 (#17289)
1. List all supported ops.
2. Demo usage in two modes.
3. Limitations.

---------

Co-authored-by: Randy Shuai <rashuai@microsoft.com>
2023-08-30 12:48:36 -07:00
BoarQing
3a4d91fafa
[VitisAI] fix doc after the support of Visual Studio 2019 is removed. (#17250)
### Description
<!-- Describe your changes. -->
Update 2019 to 2022


### 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. -->
It is required because Visual Studio is no longer a valid cmake
generator for onnxruntime.

Co-authored-by: Yueqing Zhang <yueqingz@amd.com>
2023-08-22 10:08:14 -07:00
Sheil Kumar
d910737bdf
Update DirectML-ExecutionProvider.md (#17229)
Update DirectML-ExecutionProvider.md to reflect the current update to
1.12.1 and support up to opset 17.
2023-08-21 09:11:14 -07:00
Vrajang Parikh
de3393b725
Update macOS and iOS custom build documentation for training (#17223)
### Description
Add instructions for macOS build and training pods

Preview: https://vraspar.github.io/onnxruntime/docs/build/training.html,
https://vraspar.github.io/onnxruntime/docs/build/custom.html#ios

---------

Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
Co-authored-by: Baiju Meswani <baijumeswani@gmail.com>
2023-08-18 15:09:29 -07:00
Vrajang Parikh
fcd241f145
Add iOS On Device Training Tutorial with ONNX Runtime (#17146)
### Description

This pull request introduces comprehensive tutorial for performing on
device training on iOS devices using Objective-C/Swift on device
training APIs.

Preview:
https://vraspar.github.io/onnxruntime/docs/tutorials/on-device-training/ios-app.html
Example App:
https://github.com/microsoft/onnxruntime-training-examples/tree/master/on_device_training/mobile/ios/MyVoice

---------

Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
Co-authored-by: Baiju Meswani <baijumeswani@gmail.com>
2023-08-17 00:58:22 -07:00
Scott McKay
c6ac91ee86
Update CoreML-ExecutionProvider.md supported operators (#16842) 2023-08-10 15:32:40 -07:00
Vrajang Parikh
ab90551852
add installation instruction for training pods (#17080)
### Description

Add instruction to install training CocoaPods


### Preview

https://vraspar.github.io/onnxruntime/docs/install/#training-phase---on-device-training

---------

Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
Co-authored-by: Baiju Meswani <bmeswani@microsoft.com>
2023-08-10 10:16:30 -07:00
Tianlei Wu
e1b7cd00f8
Update CUDA EP Requirements of ORT 1.15.* (#17081)
Add CUDA and cuDNN versions for ORT 1.15.
Add VC Runtime 

### 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. -->

https://github.com/microsoft/onnxruntime/issues/16967
2023-08-09 13:34:08 -07:00
Vinayak Nayak
67862b7c58
Fix typo in OpenVINO-ExecutionProvider.md (#17026)
### Description
Fixed typo (alvailable -> available) in OpenVINO-ExecutionProvider.md
file.



### Motivation and Context
This change will make the reading experience of docs better.
2023-08-07 10:10:42 -04:00
andyluo7
e7920e46c2
Update Vitis-AI-ExecutionProvider.md (#16951)
Update the download links

### Description
Update the download link of updated ONNXRT Vitis AI EP .zip archive
Update the contents of updated ONNXRT Vitis AI EP .zip archive 



### Motivation and Context
Recently we updated the Vitis AI EP for compiler enhancement and bug
fix.
The download URL of new .zip archive is changed so we need to update
this md file.
2023-07-31 22:59:22 -07:00
Yifan Li
ff415eac34
Improve TRT doc and advance EP session option (#16868)
### Description
Move EP session option usage in the front of TRT EP configuration
chapter, as it's preferred method of configuring TRT EP.

#### Major:
* Add more description for TRT EP session options
* Mark TRT environment variable as deprecated and fold the content

#### Minor:
* Fix incorrect types in one-to-one mapping table
* Fold long code example to shorten the paragraph


### Preview
After change:
https://yf711.github.io/onnxruntime/docs/execution-providers/TensorRT-ExecutionProvider.html#configurations
Before change:
https://onnxruntime.ai/docs/execution-providers/TensorRT-ExecutionProvider.html#execution-provider-options
2023-07-28 11:15:01 -07:00
Yifan Li
e7464cd41d
Fix corrupt markdown table (#16767)
### Description
* Update table markdown following
https://just-the-docs.com/docs/ui-components/tables to fix UI

* Preview:
*
https://yf711.github.io/onnxruntime/docs/execution-providers/TensorRT-ExecutionProvider.html#requirements

### Motivation and Context
https://github.com/microsoft/onnxruntime/issues/16759
2023-07-20 12:18:04 +02:00
Sayan Shaw
85719a2a9d
remove unneeded no-toc from superres (#16682)
Co-authored-by: Sayan Shaw <sayanshaw@microsoft.com>
2023-07-13 17:10:32 -07:00
Yifan Li
b4592d69c2
Clarify TRTEP doc (#16537)
### Description
* Clarify TRTEP version info


### Motivation and Context
https://github.com/microsoft/onnxruntime/issues/15118: issue to request
https://github.com/microsoft/onnxruntime/pull/16465: previous PR to
update trtep doc
2023-07-06 17:45:54 -07:00
Maanav Dalal
2bec00816b
Added (hidden) converter team page. (#16507)
Co-authored-by: MaanavD <maanavdalal@microsoft.com>
2023-07-03 15:28:11 -05:00
Ted Themistokleous
a4a5006077
Fix name for ROCMExecutinProvider in ROcm-ExecutionProvider docs (#16534)
Invalid EP name which causes confusion for users who use
ROCMExecutionProvider

Co-authored-by: Ted Themistokleous <tthemist@amd.com>
2023-06-30 11:33:43 +08:00
yf711
f240999167
Update trtep doc with ort 1.15 (#16465)
### Description
* TRT/cuda/cuDNN version updated
* Update the instruction of using trt builtin parser (new default
option) and using open-sourced onnx-trt parser (non-default)
* Add more comments to examples

Rendered version: 
1. https://yf711.github.io/onnxruntime/docs/build/eps.html#tensorrt
2.
https://yf711.github.io/onnxruntime/docs/execution-providers/TensorRT-ExecutionProvider.html
2023-06-23 12:05:11 -07:00
Preetha Veeramalai
ea3af6cadb
Update documentation for OVEP v5.0 release (#16441)
### Description
Documentation updates



### Motivation and Context
Update the OpenVINO Execution Provider and build documentations for
1.15.0 release.
2023-06-23 10:39:20 -07:00
Nat Kershaw (MSFT)
1b61ac0517
Update compatibility.md for release 1.15 (#16389) 2023-06-16 11:53:50 -07:00
Baiju Meswani
307d5afe5f
Add On Device Training Tutorial with ONNX Runtime (#16167) 2023-06-15 16:01:26 -07:00
Jeff Mendenhall
28d1c4473f
Update Blog page and Move Vitis AI EP from community maintained to main EP list (#16290)
### Description
Move Vitis AI EP from community maintained to main EP list



### 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. -->
2023-06-10 07:25:52 -07:00