[Cherry-Pick][Loader][BugFix] Fix some parameters place on CPU in PaddleOCR-VL (#5413)

[SigureMo]

Motivation

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick，PR标题需遵循格式，在最开始加上[Cherry-Pick]标签，以及最后面加上原PR ID，例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

cherry-pick of #5413

Modifications

see #5413

Usage or Command

see #5413

Accuracy Tests

无

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!

[Copilot]

Pull request overview

This cherry-pick PR from #5413 fixes parameter placement issues on CPU in PaddleOCR-VL models by ensuring proper device handling during weight loading. The changes replace direct param.copy_ calls with the h2d_copy utility function, which handles cross-device tensor copying correctly for both GPU and CPU platforms.

Key changes:

• Replace param.copy_ with h2d_copy for proper device-aware tensor copying
• Add parameter initialization checks before weight loading
• Add missing h2d_copy import in projector.py

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
fastdeploy/model_executor/models/paddleocr_vl/siglip.py	Updated three weight_loader methods (out_proj_weight_loader and SiglipMLP.weight_loader) to use h2d_copy and add initialization checks
fastdeploy/model_executor/models/paddleocr_vl/projector.py	Added h2d_copy import and updated weight_loader method in Projector class with initialization check and h2d_copy usage

[codecov-commenter]

Codecov Report

❌ Patch coverage is 70.00000% with 3 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/2.4@7eea23f). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
...eploy/model_executor/models/paddleocr_vl/siglip.py	66.66%	0 Missing and 2 partials ⚠️
...oy/model_executor/models/paddleocr_vl/projector.py	75.00%	0 Missing and 1 partial ⚠️

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.4    #5414   +/-   ##
==============================================
  Coverage               ?   59.09%           
==============================================
  Files                  ?      326           
  Lines                  ?    40336           
  Branches               ?     6117           
==============================================
  Hits                   ?    23838           
  Misses                 ?    14659           
  Partials               ?     1839           

Flag	Coverage Δ
GPU	59.09% <70.00%> (?)

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.