Fixed the calib size bug

[jingyu-ml]

What does this PR do?

Type of change: Bug fix

Usage

# Add a code snippet demonstrating how to use this

Testing

Before your PR is "Ready for review"

Make sure you read and follow Contributor guidelines and your commits are signed (git commit -s -S).

Make sure you read and follow the Security Best Practices (e.g. avoiding hardcoded trust_remote_code=True, torch.load(..., weights_only=False), pickle, etc.).

• Is this change backward compatible?: ✅ / ❌ / N/A
• If you copied code from any other sources or added a new PIP dependency, did you follow guidance in CONTRIBUTING.md: ✅ / ❌ / N/A
• Did you write any new necessary tests?: ✅ / ❌ / N/A
• Did you update Changelog?: ✅ / ❌ / N/A

Additional Information

Summary by CodeRabbit

• Bug Fixes
  • Fixed quantization configuration calibration batch counting to properly account for partial final batches during the calibration process.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[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: Pro

Run ID: bd0793df-4ffd-4cd7-90b6-c922c126c2ad

📥 Commits

Reviewing files that changed from the base of the PR and between df80a0f and 5b747a4.

📒 Files selected for processing (1)

• examples/diffusers/quantization/quantize_config.py

---

📝 Walkthrough

Walkthrough

The change modifies the calibration batch count calculation in CalibrationConfig.num_batches to use ceiling division instead of floor division, ensuring that partial final batches are counted when computing the number of calibration batches required.

Changes

Cohort / File(s)	Summary
Calibration Config Update examples/diffusers/quantization/quantize_config.py	Added math import and updated num_batches property from floor division (//) to ceiling division (math.ceil()), ensuring partial final batches are included in the batch count.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 3 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Title check	❓ Inconclusive	The title 'Fixed the calib size bug' is vague and uses generic language ('bug') without clearly specifying what was actually changed. While it references 'calib size,' a reviewer cannot understand from the title alone that this involves changing floor division to ceiling division in CalibrationConfig.num_batches.	Use a more specific title like 'Fix CalibrationConfig to use ceiling division for batch calculation' to clearly convey the technical change being made.

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
Security Anti-Patterns	✅ Passed	PR modifies quantize_config.py with math import and ceiling division bug fix, with no security anti-patterns detected.

_{✏️ 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 jingyux/diffusion-calib-size-bug

---

_{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.
2026-04-06 13:48 UTC

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 76.05%. Comparing base (df80a0f) to head (5b747a4).
⚠️ Report is 2 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1178      +/-   ##
==========================================
+ Coverage   74.77%   76.05%   +1.28%     
==========================================
  Files         351      351              
  Lines       40072    40072              
==========================================
+ Hits        29964    30478     +514     
+ Misses      10108     9594     -514     

Flag	Coverage Δ
examples	43.85% <ø> (+3.63%)	⬆️
unit	54.74% <ø> (-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.

[Edwardf0t1]

LGTM

[kevalmorabia97]

/ok to test 5b747a4