[V1][BUGFIX][0.10.1] FIX mtp on main branch

[JC-ut0]

What this PR does / why we need it?

Fix MTP torchair bug caused by torchair refactor and moe refactor

Depends on PRs:
fused moe fix: #2627
torchair multi DP fix: #2626

Does this PR introduce any user-facing change?

when dp is enabled, to run mtp online server, need to disable server log due to the current metrics does not support multi dp
--disable-log-stats

How was this patch tested?

• vLLM version: v0.10.1.1
• vLLM main: vllm-project/vllm@7c8271c

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

[gemini-code-assist]

Code Review

This pull request appears to be a bugfix for Multi-Token Prediction (MTP) on the main branch. The changes involve selecting the correct MTP model implementation (TorchairDeepSeekMTP) when torchair graph is enabled, and updating the quantization logic for FusedMoE. I've found a critical issue in the FusedMoE quantization logic where a layer that should be skipped would be incorrectly quantized due to an unconditional assignment. I've provided a suggestion to fix this logical error.

[MengqingCao]

Plz add more details in pr message to describe the specific issue this pr fixes

[github-actions]

This pull request has conflicts, please resolve those before we can evaluate the pull request.

[MengqingCao]

lgtm

[codecov]

Codecov Report

❌ Patch coverage is 83.33333% with 3 lines in your changes missing coverage. Please review.
✅ Project coverage is 73.57%. Comparing base (600b08f) to head (ece0890).
⚠️ Report is 16 commits behind head on main.

Files with missing lines	Patch %	Lines
vllm_ascend/worker/mtp_proposer_v1.py	25.00%	3 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2632      +/-   ##
==========================================
+ Coverage   72.61%   73.57%   +0.96%     
==========================================
  Files         147      151       +4     
  Lines       21805    21945     +140     
==========================================
+ Hits        15833    16147     +314     
+ Misses       5972     5798     -174     

Flag	Coverage Δ
unittests	73.57% <83.33%> (+0.96%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ 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.

[MengqingCao]

Let's merge this first as the failed CI cases is not introduced in this pr, will fix in #2687