[XPU] handle inplace return value for XPU.

[Jiajun-Ji]

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)

单测修复

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 主要用于修复 XPU 场景下单测对自定义算子 speculate_set_value_by_flags_and_idx 的返回值处理：XPU 侧算子表现为 in-place 更新输入张量，因此单测不应依赖其返回值再取 .numpy()。

Changes:

• XPU 分支不再接收 speculate_set_value_by_flags_and_idx 的返回值，改为直接读取被原地更新后的 pre_ids_all。
• 非 XPU 分支保持原先逻辑：使用算子返回的 Tensor 并转换为 numpy 进行对比校验。

[PaddlePaddle-bot]

🤖 AI Code Review | 2026-04-17 16:44 CST

📋 Review 摘要

PR 概述：修复 XPU 平台 speculate_set_value_by_flags_and_idx 单测中对 inplace 返回值的处理方式
变更范围：custom_ops/xpu_ops/test/
影响面 Tag：XPU OP

📝 PR 规范检查

PR 标题包含 [XPU] Tag ✅；描述中 Motivation 仅写了"单测修复"，建议补充更具体的说明，例如：

描述建议（可直接复制）：

Motivation：XPU 版本的 speculate_set_value_by_flags_and_idx 算子通过 inplace 方式修改 pre_ids_all，C++ 函数返回 void，不应使用返回值。修复单测以直接从 pre_ids_all 读取结果，并将 GPU 分支的 .numpy() 调用移入 else 块以修正缩进逻辑。

Modifications：修正 XPU 分支不再捕获返回值，改为直接读取 inplace 修改后的 pre_ids_all；将 GPU 分支的 out_xpu.numpy() 缩进到 else 块内，避免 XPU 分支执行时引用未定义的返回值。

问题

未发现阻塞性问题。

代码分析

已验证 XPU 算子的 C++ 实现（speculate_set_value_by_flags.cc）：

• 函数签名为 void SpeculateSetValueByFlagsAndIdx(...)，确认无返回值
• PD_BUILD_STATIC_OP 使用 .SetInplaceMap({{"pre_ids_all", "pre_ids_all_out"}}) 声明 inplace 语义
• 修改后的测试正确地忽略返回值，直接从 pre_ids_all.numpy() 获取结果

同时确认 GPU 版本（cpp_extensions.cc pybind 暴露）同样为 void 返回，但 GPU 测试分支通过 efficientllm.ops.gpu 导入的是 static op 版本（有 inplace 返回），因此 else 分支保留 out_xpu = ... 赋值是正确的。

总体评价

变更逻辑正确，准确处理了 XPU 算子的 inplace 语义差异。out_xpu.numpy() 的缩进修复也消除了 XPU 路径下潜在的变量引用问题。

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@6847891). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #7463   +/-   ##
==========================================
  Coverage           ?   74.14%           
==========================================
  Files              ?      398           
  Lines              ?    54977           
  Branches           ?     8613           
==========================================
  Hits               ?    40762           
  Misses             ?    11484           
  Partials           ?     2731           

Flag	Coverage Δ
GPU	74.14% <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.