Fridah/kinjal/vllm modelopt reload

[Fridah-nv]

What does this PR do?

Type of change: ?

Enable vllm fakequant export in examples/llm_ptq: example command:

python ../llm_ptq/hf_ptq.py \
  --pyt_ckpt_path <MODEL_PATH> \
  --qformat nvfp4 \
  --calib_size 512 \
  --export_path <EXPORT_DIR> \
  --vllm_fakequant_export \
  --trust_remote_code

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

[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: Pro

Run ID: 758471f1-4c68-4561-ae86-6e93d047977d

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 fridah/kinjal/vllm_modelopt_reload

📝 Coding Plan

• Generate coding plan for human review comments

---

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

Tip

Flake8 can be used to improve the quality of Python code reviews.

Flake8 is a Python linter that wraps PyFlakes, pycodestyle and Ned Batchelder's McCabe script.

To configure Flake8, add a '.flake8' or 'setup.cfg' file to your project root.

See Flake8 Documentation for more details.

[realAsma]

We should remove hf_ptq_export.py -> in my understanding examples/llm_ptq/hf_ptq.py should be sufficient. Is that correct @kinjalpatel27 ?

[kinjalpatel27]

yes its sufficient. we added hf_ptq_export.py to not overcrowd the hf_ptq.py example.

[realAsma]

move this to the end of arguments

[kinjalpatel27]

also lets add a line in hf_ptq.py readme about this argument, pointing to vllm_serve readme export section

[realAsma]

Suggested change

	Alternatively, the dedicated `hf_ptq_export.py` script (**deprecated** — use `hf_ptq.py` with `--vllm_fakequant_export` instead) can be used for a simpler interface:
	```bash
	python hf_ptq_export.py \
	--pyt_ckpt_path <MODEL_PATH> \
	--quant_cfg NVFP4_DEFAULT_CFG \
	--export_path <EXPORT_DIR> \
	--trust_remote_code
	```