[6421642][ONNX][Quantization] Fix NVFP4 exporter node ordering

[gcunhase]

What does this PR do?

Type of change: Bug fix

• Adds a stable tensor-dependency sort before NVFP4QuantExporter.post_process() returns.
• Ensures newly inserted DequantizeLinear and Cast producer nodes appear before the Transpose / MatMul nodes that consume them.
• Adds CPU Torch ONNX export regression coverage for NVFP4 static weight export.

Usage

# Internal NVFP4 export path:
# 1. Quantize a torch model with an NVFP4 config.
# 2. Export it to ONNX so torch emits TRT_FP4QDQ nodes.
# 3. Lower those nodes with NVFP4QuantExporter.process_model(...).

import onnx

from modelopt.onnx.export import NVFP4QuantExporter

onnx_model = onnx.load("model_with_trt_fp4qdq.onnx")
onnx_model = NVFP4QuantExporter.process_model(onnx_model)
onnx.checker.check_model(onnx_model)

Testing

• Reproduced the issue before the fix on a small NVFP4 ONNX export graph and on main before this patch.
• Verified the fixed exporter returns producer_after_consumer_edges=0, onnx.checker.check_model(converted) passes, and the repro exits with rc=0.
• Ran python -m pytest tests/unit/torch/quantization/test_nvfp4_onnx_export_cpu.py::test_nvfp4_exported_onnx_is_topologically_sorted -q.

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

[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]

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: be49b69d-35b2-4a81-8fc3-d1b5a1b92cbf

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

---

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

[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.