Add LAQ/LSQ support and recipes

[realAsma]

Summary

• port LAQ support onto latest main
• add QAD quantize recipes for fp4 LSQ and fp4 Dual Scale LSQ only
• use modular $import recipes and set quantize_pre_scale: false
• add qad_laq_scales.yaml for scale-only QAD
• add focused recipe and LAQ behavior tests

Validation

• pre-commit run --files ...
• git diff --check
• pytest_pwd tests/unit/recipe/test_laq_recipes.py tests/unit/torch/quantization/test_laq.py (37 passed)

Parity

Compared the new recipes against the original LAQ folder reference at /home/scratch.akuriparambi_coreai/Model-Optimizer-LAQ. The two new recipes resolve to the same core LAQ algorithm and weight/input/KV/lm_head quantizer settings as the old LAQ recipes, with the new explicit quantize_pre_scale: false setting.

[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: 50d620e3-7806-4270-806e-3fd0b1d9da3a

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/laq-qad-recipes

---

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

[codecov]

Codecov Report

❌ Patch coverage is 55.80524% with 118 lines in your changes missing coverage. Please review.
✅ Project coverage is 61.13%. Comparing base (892d27a) to head (f95fdff).

Files with missing lines	Patch %	Lines
modelopt/torch/quantization/model_calib.py	14.10%	67 Missing ⚠️
...lopt/torch/kernels/quantization/gemm/fp4_kernel.py	0.00%	23 Missing ⚠️
.../torch/quantization/nn/modules/tensor_quantizer.py	82.47%	17 Missing ⚠️
modelopt/torch/quantization/tensor_quant.py	74.19%	8 Missing ⚠️
...torch/quantization/plugins/transformers_trainer.py	80.00%	3 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1884      +/-   ##
==========================================
- Coverage   61.16%   61.13%   -0.04%     
==========================================
  Files         515      515              
  Lines       57216    57474     +258     
==========================================
+ Hits        34995    35135     +140     
- Misses      22221    22339     +118     

Flag	Coverage Δ
unit	54.90% <55.80%> (-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.