docs(diffusers): clarify --calib-size is samples/prompts, not steps

[felipeofdev-ai]

Summary

Clarifies --calib-size help in examples/diffusers/quantization/quantize.py so it is not confused with denoising steps.

Changes

• Help text: number of calibration samples/prompts
• Notes ceil batching vs --batch-size
• Points users to --n-steps for denoising steps

Fixes #247

Test plan

• python quantize.py --help shows the new help string

Summary by CodeRabbit

• Documentation
  • Clarified the --calib-size option to explain calibration sample and prompt counts.
  • Documented batch-size rounding behavior.
  • Distinguished calibration size from denoising steps configured with --n-steps.

---

— Felipe Fernandes · Systems & Agentic AI Engineer
https://github.com/felipeofdev-ai · https://felipeofdev-ai.github.io/

Summary by CodeRabbit

• Documentation
  • Added --calib-samples as an alternative to --calib-size.
  • Clarified calibration prompts, sample handling, batch-size rounding, and denoising-step configuration.

[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: Enterprise

Run ID: 0e3904b3-2c63-4c9e-9cd5-5155f1d657cc

📥 Commits

Reviewing files that changed from the base of the PR and between e642dda and 81508cf.

📒 Files selected for processing (1)

• examples/diffusers/quantization/quantize.py

🚧 Files skipped from review as they are similar to previous changes (1)

• examples/diffusers/quantization/quantize.py

---

📝 Walkthrough

Walkthrough

The calibration CLI now accepts --calib-samples as an alias for --calib-size. Its help text explains calibration prompt counts, batch-size rounding, and the separate --n-steps denoising-step option.

Changes

Calibration CLI documentation

Layer / File(s)	Summary
Clarify calibration size help text examples/diffusers/quantization/quantize.py	The CLI adds --calib-samples as an alias for --calib-size. The help text describes calibration samples and prompts, batch-size rounding, and the separate --n-steps option.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Suggested reviewers: jingyu-ml

🚥 Pre-merge checks | ✅ 6

✅ Passed checks (6 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly describes the main change: clarifying that --calib-size counts samples or prompts, not steps.
Linked Issues check	✅ Passed	The changes satisfy issue #247 by clarifying sample semantics, batch-size rounding, denoising steps, and adding the --calib-samples alias.
Out of Scope Changes check	✅ Passed	All reported changes support the linked issue and the stated objective of clarifying --calib-size behavior.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Security Anti-Patterns	✅ Passed	The commit only changes CLI help and adds --calib-samples; no prohibited security patterns, # nosec comments, or dependency-manifest changes were introduced.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[felipeofdev-ai]

Thanks for reviewing — CI is green on my side. Happy to adjust anything you need.

— Felipe Fernandes · Systems & Agentic AI Engineer
https://github.com/felipeofdev-ai · https://felipeofdev-ai.github.io/