Add Quantizers for Qwen3VLMoeTextDecoderLayer

[soodoshll]

What does this PR do?

Type of change: ? new feature

Overview: ? huggingface transformers library implements Qwen3VL Moe layer as a monolithic module, instead of assembling it using Linear layers, which cannot be recognized by modelopt's quantizer now. This PR introduces a conversion from hf's qwen3vl_moe MoE layers to qewn3_moe MoE layers which consist of a set of Linear layers.

Testing

Tested with

python hf_ptq.py --pyt_ckpt_path=Qwen/Qwen3-VL-30B-A3B-Instruct --qformat=nvfp4 --dataset wikipedia

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/No
• 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

[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.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 74.46%. Comparing base (5a4242f) to head (e0d2121).
⚠️ Report is 2 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #666      +/-   ##
==========================================
- Coverage   74.52%   74.46%   -0.06%     
==========================================
  Files         183      183              
  Lines       18400    18410      +10     
==========================================
- Hits        13712    13709       -3     
- Misses       4688     4701      +13     

☔ 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.

[shengliangxu]

I'm thinking of whether we want to directly add support to Qwen3VLMoeTextSparseMoeBlock, it feels a bit fragile to use a replacement module.

[soodoshll]

I've refactored this part.