[BugFix] fix dynamic c8 in v1 loader

[yuanlehome]

Motivation

fix dynamic c8 in v1 loader

💡 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)

Modifications

Usage or Command

Accuracy Tests

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

该 PR 修复了 v1 loader 中处理动态 c8（cache 量化）的一个 bug。具体来说，修复了在使用 block_wise_fp8 量化类型时，process_weights_after_loading 方法错误地尝试访问不存在的 scale 参数的问题。

关键改动

• 在 process_weights_after_loading 方法中添加条件检查，仅在非 block_wise 量化类型时才处理 cache scale 参数
• 该修复使 v1 loader 的行为与 v0 loader（process_loaded_weights 方法）保持一致

[Copilot]

新增的针对 block_wise_fp8 量化类型的条件分支缺少测试覆盖。建议在 tests/quantization/test_kv_cache.py 中添加测试用例，验证：

1. 当 cache_quant_type_str 包含 "block_wise" 时，process_weights_after_loading 不会尝试访问或设置 cache_k_out_scale 和 cache_v_out_scale
2. 当 cache_quant_type_str 不包含 "block_wise" 时，正常执行现有逻辑

这将确保该修复在未来的代码变更中保持正确性。

[codecov-commenter]

Codecov Report

❌ Patch coverage is 40.00000% with 3 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@722de5a). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
...loy/model_executor/layers/quantization/kv_cache.py	40.00%	0 Missing and 3 partials ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5562   +/-   ##
==========================================
  Coverage           ?   60.87%           
==========================================
  Files              ?      329           
  Lines              ?    41161           
  Branches           ?     6275           
==========================================
  Hits               ?    25055           
  Misses             ?    14213           
  Partials           ?     1893           

Flag	Coverage Δ
GPU	60.87% <40.00%> (?)

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.

[gongshaotian]

LGTM