fix(quantization): accept QuantizeAlgorithmConfig in get_modelike_from_algo_cfg (#201)

[realAsma]

Fixes #201

get_modelike_from_algo_cfg was typed to accept QuantizeAlgoCfgType (which includes QuantizeAlgorithmConfig instances), but the body only handled list / str / None / dict and raised ValueError("Invalid config type") for QuantizeAlgorithmConfig instances. This broke the documented pattern of passing typed config objects (MaxCalibConfig, AWQLiteCalibConfig, etc.) via quant_config['algorithm'].

The fix pre-converts a QuantizeAlgorithmConfig instance to its model_dump() dict at function entry, so the existing dict path handles it unchanged. Two-line change; no new branch needed.

Verification: added a unit test in tests/unit/torch/quantization/test_mode.py that builds a MaxCalibConfig, calls get_modelike_from_algo_cfg on both the object and its equivalent dict, and asserts the two paths produce the same tuple. Also covers the list-of-object path.

Opened by OnCallBot on behalf of realAsma. Please review the diff before merging.

cc Chenjie Luo (module owner for torch.quantization)

Summary by CodeRabbit

• New Features

  • get_modelike_from_algo_cfg now accepts configuration objects directly alongside existing input formats.

• Tests

  • Added regression test to verify configuration object handling works correctly.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 6e0a6a62-53b5-432f-824b-f80ab0bb2567

📥 Commits

Reviewing files that changed from the base of the PR and between c9098b6 and 2ade0e2.

📒 Files selected for processing (2)

• modelopt/torch/quantization/mode.py
• tests/unit/torch/quantization/test_mode.py

---

📝 Walkthrough

Walkthrough

This PR resolves a type-hint discrepancy in get_modelike_from_algo_cfg by adding support for QuantizeAlgorithmConfig instances. The function now converts config objects to dictionaries before processing, and a regression test validates the new capability.

Changes

QuantizeAlgorithmConfig Input Support

Layer / File(s)	Summary
Config object handling in get_modelike_from_algo_cfg modelopt/torch/quantization/mode.py	get_modelike_from_algo_cfg now detects QuantizeAlgorithmConfig instances and converts them to dictionaries using model_dump() before proceeding with existing parsing logic.
Regression test for QuantizeAlgorithmConfig input tests/unit/torch/quantization/test_mode.py	Test module imports MaxCalibConfig and get_modelike_from_algo_cfg, then verifies the function accepts config objects by comparing object-based and dict-based inputs for equality, asserting the dumped config appears in the result, and confirming list-wrapped inputs behave consistently.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

🚥 Pre-merge checks | ✅ 5 | ❌ 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 (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately describes the main change: accepting QuantizeAlgorithmConfig instances in get_modelike_from_algo_cfg function.
Linked Issues check	✅ Passed	The PR fully addresses issue #201 by implementing support for QuantizeAlgorithmConfig instances in get_modelike_from_algo_cfg and includes a comprehensive test.
Out of Scope Changes check	✅ Passed	All changes are directly scoped to fixing the issue: the core fix in mode.py and the regression test in test_mode.py are both necessary and related.
Security Anti-Patterns	✅ Passed	No security anti-patterns detected. Changes use safe model_dump() conversion; no torch.load, numpy.load, trust_remote_code, eval, exec, nosec, or new dependencies present.

_{✏️ 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 oncallbot/fix-201

---

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

[github-actions]

PR Preview Action v1.8.1
Preview removed because the pull request was closed.
2026-05-21 22:39 UTC

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 76.72%. Comparing base (c9098b6) to head (2ade0e2).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1528      +/-   ##
==========================================
- Coverage   76.75%   76.72%   -0.03%     
==========================================
  Files         476      476              
  Lines       51811    51813       +2     
==========================================
- Hits        39767    39756      -11     
- Misses      12044    12057      +13     

Flag	Coverage Δ
examples	41.63% <50.00%> (+0.90%)	⬆️
gpu	59.51% <50.00%> (-0.59%)	⬇️
regression	15.21% <0.00%> (+0.07%)	⬆️
unit	52.62% <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.