Support layerwise VLM image calibration in hf_ptq

[realAsma]

Summary

• route layerwise VLM image calibration through the full VLM wrapper so multimodal forwards reach patched decoder layers
• keep non-layerwise VLM image calibration on the extracted language model
• add focused mock coverage for both branches

Validation

• pytest_pwd tests/examples/hf_ptq/test_hf_ptq_mono_quantize.py tests/examples/hf_ptq/test_hf_ptq_args.py
• pre-commit run --files examples/hf_ptq/hf_ptq.py tests/examples/hf_ptq/test_hf_ptq_mono_quantize.py

[copy-pr-bot]

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]

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 18d02343-c97f-4d5a-bc45-44a0acb08fdd

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch asma/vlm-layerwise-calibration

---

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