Skip to content

[AMD] Document QuarkQuantization in quantization docs#2533

Open
thpereir wants to merge 1 commit into
microsoft:mainfrom
thpereir:quark-0.12-docs
Open

[AMD] Document QuarkQuantization in quantization docs#2533
thpereir wants to merge 1 commit into
microsoft:mainfrom
thpereir:quark-0.12-docs

Conversation

@thpereir

@thpereir thpereir commented Jun 19, 2026

Copy link
Copy Markdown

Describe your changes

Adds documentation for the QuarkQuantization pass (AMD Quark), which was previously absent from the Olive quantization docs.

  • Adds an AMD Quark section to the quantization feature guide (docs/source/features/quantization.md) covering both the ONNX and Torch LLM backends, with example configs for each use case.
  • Adds a QuarkQuantization entry to the pass API reference (docs/source/reference/pass.rst).

This is a docs-only change, independent of #2532.

Checklist before requesting a review

  • Add unit tests for this change.

  • Make sure all tests can pass.

  • Update documents if necessary.

  • Lint and apply fixes to your code by running lintrunner -a

  • Is this a user-facing change? If yes, give a description of this change to be included in the release notes.

    Users can now find QuarkQuantization in the quantization documentation at https://microsoft.github.io/Olive/features/quantization.html.

(Optional) Issue link

@thpereir thpereir marked this pull request as ready for review June 22, 2026 20:00
Copilot AI review requested due to automatic review settings June 22, 2026 20:00

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds missing documentation for the AMD Quark-backed QuarkQuantization pass, integrating it into both the feature guide and the pass reference so users can discover the pass and its configuration.

Changes:

  • Adds an “AMD Quark” section to the quantization feature guide, including brief backend descriptions and example configs (ONNX + HuggingFace PyTorch).
  • Adds a QuarkQuantization entry (with an anchor) to the pass reference page.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File Description
docs/source/reference/pass.rst Adds a reference/anchor entry for QuarkQuantization in the pass catalog.
docs/source/features/quantization.md Adds an AMD Quark section describing QuarkQuantization and providing example configurations.

Comment thread docs/source/features/quantization.md
Add an AMD Quark section to the quantization feature guide covering the
ONNX and Torch backends with example configs, and add a pass reference
entry for QuarkQuantization.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants