Fix NVFP4 multi-GPU export device handling

[realAsma]

What does this PR do?

Type of change: Bug fix

NVFP4 weight export could allocate intermediate tensors on the process's current CUDA device instead of the input tensor's device. This caused export failures when a model shard lived on a different GPU. This change scopes NVFP4 quantization to the input device while restoring the caller's current device afterward.

The export path also now uses the quantizer's public is_enabled state instead of inferring that state from its formatted representation.

Usage

N/A — this fixes existing multi-GPU export behavior without changing the public API.

Testing

• pre-commit run --files modelopt/torch/export/unified_export_hf.py modelopt/torch/quantization/qtensor/nvfp4_tensor.py tests/gpu/torch/quantization/test_qtensor_cuda.py tests/unit/torch/export/test_export_weight.py
• pytest tests/unit/torch/export/test_export_weight.py::test_export_quantized_weight_does_not_repr_input_quantizer -q -x
• CUDA_VISIBLE_DEVICES=1,2 pytest tests/gpu/torch/quantization/test_qtensor_cuda.py::TestQTensor::test_nvfp4_export_uses_input_device -q -x

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?: ✅
• 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?: ✅
• Did you update Changelog?: N/A — focused bug fix; no critical or previously documented release issue
• Did you get Claude approval on this PR?: N/A — draft preparation only

Additional Information

No new dependency or public API is introduced.

[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: 60f459c8-b10f-4157-81d7-5849e1ecfd33

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

---

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

[github-actions]

PR Preview Action v1.8.1
🚀 View preview at https://NVIDIA.github.io/Model-Optimizer/pr-preview/pr-2197/
Built to branch gh-pages at 2026-08-14 21:46 UTC. Preview will be ready when the GitHub Pages deployment is complete.

[codecov]

Codecov Report

❌ Patch coverage is 73.07692% with 7 lines in your changes missing coverage. Please review.
✅ Project coverage is 78.96%. Comparing base (5e887aa) to head (25819df).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
...odelopt/torch/quantization/qtensor/nvfp4_tensor.py	68.18%	7 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2197      +/-   ##
==========================================
- Coverage   78.97%   78.96%   -0.01%     
==========================================
  Files         522      522              
  Lines       60606    60612       +6     
==========================================
  Hits        47862    47862              
- Misses      12744    12750       +6     

Flag	Coverage Δ
unit	55.57% <73.07%> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 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.