Skip to content

use typed quantize config instead of a raw dict#1249

Merged
shengliangxu merged 5 commits intomainfrom
shengliangx/use-typed-config
Apr 14, 2026
Merged

use typed quantize config instead of a raw dict#1249
shengliangxu merged 5 commits intomainfrom
shengliangx/use-typed-config

Conversation

@shengliangxu
Copy link
Copy Markdown
Collaborator

@shengliangxu shengliangxu commented Apr 13, 2026 •
edited by coderabbitai bot
Loading

What does this PR do?

But fix:

Use typed QuantizeConfig instead using raw dict for formal typed ModelOpt configs.

The dict typing was accidental.

Summary by CodeRabbit

  • Refactor

    • Quantization recipe configuration is now implemented with a strongly-typed, structured schema that enforces type safety and provides enhanced validation with comprehensive error detection capabilities.

  • Tests

    • Updated recipe loading tests to correctly validate quantization configurations when recipes are loaded from directories, fully supporting the new structured object-based configuration format.

@shengliangxu
use typed quantize config instead of a raw dict
fc48c3c 
Signed-off-by: Shengliang Xu <shengliangx@nvidia.com>
@copy-pr-bot
Copy link
Copy Markdown

copy-pr-bot bot commented Apr 13, 2026

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai bot commented Apr 13, 2026 •
edited
Loading

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 7acba763-eadf-4201-b38d-8cdba8b2a851

📥 Commits

Reviewing files that changed from the base of the PR and between 14b78ae and 7671387.

📒 Files selected for processing (3)
  • examples/llm_ptq/hf_ptq.py
  • modelopt/recipe/config.py
  • tests/unit/recipe/test_loader.py
📝 Walkthrough

Walkthrough

The changes introduce type safety to the quantization configuration by replacing an untyped dictionary with a strongly typed QuantizeConfig object in the PTQ recipe configuration. Related code and tests are updated to work with the structured type instead of plain dictionaries.

Changes

Cohort / File(s) Summary
Config Type Strengthening
modelopt/recipe/config.py		 The quantize field in ModelOptPTQRecipe changes from dict[str, Any] with default {} to QuantizeConfig with instantiated default QuantizeConfig(). Adds import of QuantizeConfig and removes unused Any import.
Usage Update
examples/llm_ptq/hf_ptq.py		 Calls .model_dump() on the recipe.quantize object to convert it to a plain dictionary representation when assigning to quant_cfg for downstream quantization logic.
Test Updates
tests/unit/recipe/test_loader.py		 Adjusts assertions in test_load_recipe_dir to access recipe.quantize properties as object attributes (recipe.quantize.algorithm, recipe.quantize.quant_cfg) rather than dictionary keys.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~12 minutes

🚥 Pre-merge checks | ✅ 3 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Docstring Coverage ⚠️ Warning Docstring coverage is 66.67% which is insufficient. The required threshold is 80.00%. Write docstrings for the functions missing them to satisfy the coverage threshold.
✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title accurately summarizes the main change: replacing an untyped dict for quantize configuration with a formally typed QuantizeConfig object.
Security Anti-Patterns ✅ Passed All three modified files contain no security anti-patterns from SECURITY.md including unsafe deserialization, hardcoded remote code execution flags, dynamic code execution, or security bypass comments.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
📝 Generate docstrings
  • Create stacked PR
  • Commit on current branch
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch shengliangx/use-typed-config

Comment @coderabbitai help to get the list of available commands and usage tips.

@github-actions
Copy link
Copy Markdown
Contributor

github-actions bot commented Apr 13, 2026 •
edited
Loading

PR Preview Action v1.8.1
Preview removed because the pull request was closed.
2026-04-14 01:25 UTC

@shengliangxu
default_factory -> default
f8bceea 
safe from Pydantic v2

Signed-off-by: Shengliang Xu <shengliangx@nvidia.com>
@shengliangxu shengliangxu marked this pull request as ready for review April 13, 2026 20:59
@shengliangxu shengliangxu requested a review from a team as a code owner April 13, 2026 20:59
@shengliangxu shengliangxu requested a review from Edwardf0t1 April 13, 2026 20:59
@codecov
Copy link
Copy Markdown

codecov bot commented Apr 13, 2026 •
edited
Loading

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 77.44%. Comparing base (202c3d3) to head (d5d179a).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files 
@@            Coverage Diff             @@
##             main    #1249      +/-   ##
==========================================
+ Coverage   76.90%   77.44%   +0.54%     
==========================================
  Files         350      350              
  Lines       40524    40524              
==========================================
+ Hits        31166    31385     +219     
+ Misses       9358     9139     -219
Flag Coverage Δ
examples 43.80% <100.00%> (+1.17%) ⬆️
gpu 57.43% <100.00%> (-0.11%) ⬇️
unit 55.61% <100.00%> (+0.01%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

cjluo-nv
cjluo-nv approved these changes Apr 14, 2026
View reviewed changes
Copy link
Copy Markdown
Collaborator

@cjluo-nv cjluo-nv left a comment

Choose a reason for hiding this comment

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

Small, well-scoped bug fix (6 lines changed across 3 files). Changes ModelOptPTQRecipe.quantize from dict[str, Any] to the proper typed QuantizeConfig, fixing an accidental raw-dict typing. The hf_ptq.py example correctly calls .model_dump() to convert back to a dict where downstream code expects dict operations (.append(), copy.deepcopy(), subscript access). Tests are updated to match the new typed access pattern. The change is correct and straightforward.

@shengliangxu shengliangxu merged commit b6c6ec3 into main Apr 14, 2026
44 checks passed
@shengliangxu shengliangxu deleted the shengliangx/use-typed-config branch April 14, 2026 01:24
Edwardf0t1 pushed a commit that referenced this pull request Apr 15, 2026
@shengliangxu @Edwardf0t1
use typed quantize config instead of a raw dict (#1249)
da41d79 
### What does this PR do?

But fix:

Use typed QuantizeConfig instead using raw dict for formal typed
ModelOpt configs.

The dict typing was accidental.

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

* **Refactor**
* Quantization recipe configuration is now implemented with a
strongly-typed, structured schema that enforces type safety and provides
enhanced validation with comprehensive error detection capabilities.

* **Tests**
* Updated recipe loading tests to correctly validate quantization
configurations when recipes are loaded from directories, fully
supporting the new structured object-based configuration format.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Shengliang Xu <shengliangx@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@cjluo-nv cjluo-nv cjluo-nv approved these changes

@Edwardf0t1 Edwardf0t1 Awaiting requested review from Edwardf0t1 Edwardf0t1 is a code owner automatically assigned from NVIDIA/modelopt-examples-llm_ptq-codeowners

@meenchen meenchen Awaiting requested review from meenchen

@sychen52 sychen52 Awaiting requested review from sychen52

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@shengliangxu @cjluo-nv