Add ortpackage recipes#491
Open
xiaoyu-work wants to merge 5 commits into
Open
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Adds new .ortpackage recipe documentation and supporting files to package and run Qwen3.5-0.8B and Phi-4-mini-reasoning with ONNX Runtime GenAI, including export (CPU/GPU), package generation, and inference usage.
Changes:
- Added ortpackage usage guides + minimal dependency lists for
Qwen/Qwen3.5-0.8Bandmicrosoft/Phi-4-mini-reasoning. - Added per-recipe
.gitignorerules to exclude generated CPU/GPU export folders and produced.ortpackageartifacts. - Extended the Phi-4-mini-reasoning OpenVINO recipe README with an ortpackage generation command, plus an ignore rule for the generated package.
Reviewed changes
Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| Qwen-Qwen3.5-0.8B/ortpackage/README.md | New end-to-end ortpackage recipe guide (export CPU/GPU, package, run inference). |
| Qwen-Qwen3.5-0.8B/ortpackage/requirements.txt | Adds dependencies needed for the ortpackage workflow. |
| Qwen-Qwen3.5-0.8B/ortpackage/.gitignore | Ignores generated export outputs and package directory. |
| microsoft-Phi-4-mini-reasoning/ortpackage/README.md | New end-to-end ortpackage recipe guide (export CPU/GPU, package, run inference). |
| microsoft-Phi-4-mini-reasoning/ortpackage/requirements.txt | Adds dependencies needed for the ortpackage workflow. |
| microsoft-Phi-4-mini-reasoning/ortpackage/.gitignore | Ignores generated export outputs and package directory. |
| microsoft-Phi-4-mini-reasoning/OpenVINO/README.md | Adds instructions to combine OpenVINO outputs into a .ortpackage. |
| microsoft-Phi-4-mini-reasoning/OpenVINO/.gitignore | Ignores the generated OpenVINO ortpackage output. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
This file contains hidden or 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
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.
This pull request adds new documentation, usage recipes, and supporting files to enable packaging both the Qwen3.5-0.8B and Phi-4-mini-reasoning models into ONNX Runtime
.ortpackageformat for GenAI workflows. It introduces step-by-step guides for exporting CPU and GPU variants, combining them, and running inference, as well as updating.gitignoreand requirements for these workflows.ONNX Runtime ortpackage support and documentation:
README.mdguides for bothQwen-Qwen3.5-0.8B/ortpackageandmicrosoft-Phi-4-mini-reasoning/ortpackagedirectories, describing how to export Hugging Face models to ONNX (CPU/GPU), combine them into a.ortpackage, and run inference usingonnxruntime-genai. [1] [2].gitignorefiles inQwen-Qwen3.5-0.8B/ortpackage,microsoft-Phi-4-mini-reasoning/ortpackage, andmicrosoft-Phi-4-mini-reasoning/OpenVINOto exclude generated CPU/GPU folders and.ortpackageartifacts. [1] [2]requirements.txtfiles specifying dependencies onolive-ai[mobius-ai]andonnxruntime-genaifor both model directories.microsoft-Phi-4-mini-reasoning/OpenVINO/README.mdwith instructions for combining OpenVINO IR outputs into a.ortpackagefor GenAI runtime.