Gh-pages #22259
Closed
Gh-pages #22259
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
### Description update document for webgpu Preview: https://fs-eire.github.io/onnxruntime/docs/
…in 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. -->
Include on-device training release blog. ### Description <!-- Describe your changes. --> Included entry for on-device training release blog. ### 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. --> Provides latest updates in the blog.
### Description Documentation updates ### Motivation and Context Update the OpenVINO Execution Provider and build documentations for 1.15.0 release.
### 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
Staged here: https://natke.github.io/onnxruntime/ (The request sent by the staging site fails, as this site is not authorized the analytics backend)
) Invalid EP name which causes confusion for users who use ROCMExecutionProvider Co-authored-by: Ted Themistokleous <[email protected]>
Co-authored-by: MaanavD <[email protected]>
### Description <!-- Describe your changes. --> Update with On-Device Training Deep Dive blog details. ### 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. --> Want to publicize the deep-dive blog through the onnx runtime website.
### Description <!-- Describe your changes. --> Missed a brace in previous update. ### 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. --> - Fix break.
Co-authored-by: Sayan Shaw <[email protected]>
### 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 #16759
### 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
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.
### Description Fixed typo (alvailable -> available) in OpenVINO-ExecutionProvider.md file. ### Motivation and Context This change will make the reading experience of docs better.
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. --> #16967
### 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 <[email protected]> Co-authored-by: Baiju Meswani <[email protected]>
### 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 <[email protected]> Co-authored-by: Baiju Meswani <[email protected]>
### 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 <[email protected]> Co-authored-by: Baiju Meswani <[email protected]>
Update DirectML-ExecutionProvider.md to reflect the current update to 1.12.1 and support up to opset 17.
…#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 <[email protected]>
### Description Introduce how to use matmul_4bits_quantizer to do weight only quantization. ### Motivation and Context Add 4bit quantizer to onnx runtime doc
### Description Contains doc updates on latest OVEP 5.4 release.
### Description <!-- Describe your changes. --> Update CoreML ops lists with recent additions. ### 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. --> --------- Co-authored-by: Edward Chen <[email protected]>
Update according to the change request from NimbleEdge ### 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. -->
Likely will need to change HLJS theme for the rest. Should be good to instantly approve/merge, but feel free to review as necessary. Not currently deploying a preview as another more significant PR is being reviewed, but I can do it if requested :)
Add DirectML instructions to Phi-3 vision tutorial
Added this blog to community blogs: https://medium.com/@vadikus/running-phi-3-mistral-7b-llms-on-raspberry-pi-5-a-step-by-step-guide-185e8102e35b
Revamped Gen AI page based on Discovery interns. Preview available at: https://maanavd.github.io/onnxruntime/generative-ai --------- Co-authored-by: Nat Kershaw (MSFT) <[email protected]>
- WRITE_TO => WRITE - READ_FROM => READ
### Description While reading the docs, I came across a typo. This PR proposes to fix it. ### Motivation and Context Improve documentation.
### Description EP context cache feature design
### Description * Add CUDA/CuDNN requirements for 1.19.x * Update installation guide for cuda 11 package and nightly. * Remove a sentence for ROCm: `Alternatively, each major ORT release has a corresponding C/C++ ROCm package, found [here](https://github.com/microsoft/onnxruntime/releases/).` since onnxruntime_rocm package is not available in recent releases. ### Motivation and Context Doc is not up to date.
### Description Add download links to previous versions of onnxruntime-gpu. ### Motivation and Context There was a change in feeds recently, which make it hard to find the download links for previous versions of onnxruntime-gpu.
### Description QNN EP weight sharing docs
### Description This PR contains the steps of building onnxruntime in AIX OS. ### Motivation and Context AIX OS users can build the onnxruntime in their local env.
Added ORT 1.20 roadmap
|
You are not allowed to delete the mandatory files in this repo. Total execution time: 2.19 seconds |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Added ORT 1.20 roadmap
Description
Motivation and Context