[Cherry-Pick][CI]Fix write qknorm cache bug in speculative decoding(#5491)

[freeliuzc]

Motivation

#5491

💡 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

这是一个Cherry-Pick PR，修复了推测解码（speculative decoding）中写入qknorm缓存的bug。主要修复了三个CUDA kernel函数中的逻辑错误和控制流问题。

• 修正了判断编码器/解码器阶段的条件逻辑：从seq_lens_decoder[ori_bi] == 0改为seq_lens_encoder[ori_bi] > 0，语义更清晰准确
• 修复了控制流bug：将循环中的return改为continue，避免提前退出导致后续有效token无法处理
• 确保三种RoPE模式（qk_norm、标准、neox）的行为一致性

Reviewed changes

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

File	Description
custom_ops/gpu_ops/append_attn/speculate_write_cache_with_rope_kernel.cu	为三个kernel调用添加seq_lens_encoder参数传递，支持新的编码器/解码器阶段判断逻辑
custom_ops/gpu_ops/append_attn/speculate_write_cache_with_rope_impl.cuh	修复三个CUDA kernel函数中的逻辑判断条件和控制流问题：正确使用seq_lens_encoder区分编码/解码阶段，并将return改为continue保证循环正常执行

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (release/2.4@d67b64d). Learn more about missing BASE report.

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.4    #5617   +/-   ##
==============================================
  Coverage               ?   58.99%           
==============================================
  Files                  ?      327           
  Lines                  ?    40681           
  Branches               ?     6180           
==============================================
  Hits                   ?    24001           
  Misses                 ?    14815           
  Partials               ?     1865           

Flag	Coverage Δ
GPU	58.99% <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.