[CI] Adapt vl_model baseline changes due to Paddle update

[EmmonsCurse]

Motivation

Recent Paddle updates introduced changes to the VL model baseline, which caused mismatches in existing CI validation logic. This PR aims to align FastDeploy CI and baseline checks with the updated Paddle behavior to ensure CI correctness and stability.

Modifications

Updated CI baseline logic to adapt to the latest Paddle VL model changes.

Usage or Command

N/A

Accuracy Tests

N/A

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[paddle-bot]

Thanks for your contribution!

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@9e8c46c). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5576   +/-   ##
==========================================
  Coverage           ?   61.90%           
==========================================
  Files              ?      329           
  Lines              ?    41158           
  Branches           ?     6274           
==========================================
  Hits               ?    25477           
  Misses             ?    13767           
  Partials           ?     1914           

Flag	Coverage Δ
GPU	61.90% <ø> (?)

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.