[Do Not merge]Draft:Add NVFP4 four-over-six (4o6) adaptive activation quantization

[Fridah-nv]

Implements the adaptive per-block scale selection strategy from arxiv:2512.02010. Each 16-element activation block independently chooses between a 4-bit or 6-bit FP8 block scale (MSE/MAE/abs_max criteria), reducing quantization error vs. uniform scale encoding without requiring Blackwell hardware.

New public API:

• nvfp4_4o6_fake_quant in modelopt.torch.quantization.calib.fouroversix
• NVFP4_4O6_W4A4_CFG config (standard NVFP4 weights + 4o6 activations)
• "nvfp4_4o6" qformat in hf_ptq.py

Integration uses the existing TensorQuantizer backend mechanism (register_quant_backend("nvfp4_4o6", ...)), with dynamic per-inference amax.

What does this PR do?

Type of change: ?

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: 3f8608c5-6143-4fc4-94e8-8f96e95e1e79

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/4_6_act

📝 Coding Plan

• Generate coding plan for human review comments

---

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

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 70.16%. Comparing base (1070d89) to head (04c15a3).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1050      +/-   ##
==========================================
+ Coverage   70.10%   70.16%   +0.06%     
==========================================
  Files         221      222       +1     
  Lines       25541    25606      +65     
==========================================
+ Hits        17905    17967      +62     
- Misses       7636     7639       +3     

☔ View full report in Codecov by Sentry.
📢 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.