Fix a nvfp4 weight amax attribute issue during export

[Edwardf0t1]

What does this PR do?

Type of change: Bugfix

Overview: Fix a nvfp4 weight amax attribute issue during export, especially when calibration size is small. Context: sgl-project/sglang#14677 (comment)

Usage

python3 hf_ptq.py --pyt_ckpt_path /home/scratch.jingyux_coreai/kimi-k2/models/Kimi-K2-Thinking-BF16 --qformat nvfp4_mlp_only --export_path /home/omniml_data_3/zhiyuc/checkpoints/Kimi-K2-Thinking-NVFP4 --kv_cache_qformat none --calib_size 20 --trust_remote_code --dataset cnn_dailymail

Testing

Before your PR is "Ready for review"

• Make sure you read and follow Contributor guidelines and your commits are signed.
• Is this change backward compatible?: Yes
• Did you write any new necessary tests?: Yes/No
• Did you add or update any necessary documentation?: Yes/No
• Did you update Changelog?: Yes/No

Additional Information

[codecov]

Codecov Report

❌ Patch coverage is 20.00000% with 4 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.22%. Comparing base (307fe71) to head (0666678).
⚠️ Report is 18 commits behind head on main.

Files with missing lines	Patch %	Lines
...odelopt/torch/quantization/qtensor/nvfp4_tensor.py	20.00%	4 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #785      +/-   ##
==========================================
- Coverage   74.66%   74.22%   -0.44%     
==========================================
  Files         192      192              
  Lines       18975    19035      +60     
==========================================
- Hits        14167    14129      -38     
- Misses       4808     4906      +98     

☔ 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.

[cjluo-nv]

how about in line 265, do this:

if not hasattr(weight_quantizer, "_amax") or weight_quantizer._amax is None:
weight_quantizer.reset_amax()
enable_stats_collection(weight_quantizer)
weight_quantizer(weight)
finish_stats_collection(weight_quantizer)

So all weights have amax and you don't need the other code changes.