[CI] Set high-risk OOM tests for sequential execution

[EmmonsCurse]

Motivation

Under single-GPU parallel execution, some test cases have high memory consumption (e.g., large batch sizes, complex operators, or multi-stage inference). When executed concurrently, these tests may trigger OOM or be killed by the system, leading to flaky CI failures and increased debugging cost.

Modifications

• Identify and group high-risk OOM test cases
• Classify these tests as multi_gpu execution type
• Enforce sequential excution for these tests to avoid concurrent runs and reduce CPU memory contention

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.

[EmmonsCurse]

/skip-ci ci_iluvatar
/skip-ci ci_hpu
/skip-ci build_xpu
/skip-ci gpu_4cards_test
/skip-ci pre_ce_test
/skip-ci stable_test
/skip-ci base_test
/skip-ci logprob_test

[paddle-bot]

Thanks for your contribution!

[fastdeploy-bot]

🤖 AI Code Review | 2026-04-09

📋 Review 摘要

PR 概述：将高风险 OOM 测试标记为 multi_gpu 类型强制串行执行，避免并发导致的 OOM 问题

变更范围：scripts/coverage_run.sh、scripts/unittest_requirement.txt

影响面 Tag：[CI]

📝 PR 规范检查

✓ 标题包含有效 [CI] Tag，Motivation 和 Modifications 描述清晰，符合规范。

问题

级别	文件	概述
🟡 建议	scripts/unittest_requirement.txt:12	arctic_inference 依赖与本次 CI 变更主题无关
🟡 建议	scripts/unittest_requirement.txt:12	依赖版本与代码中提示的版本不一致
❓ 疑问	scripts/coverage_run.sh:45	测试文件硬编码方式维护性较差

总体评价

测试分类逻辑合理，能够有效避免高风险 OOM 测试并发执行导致的问题。但新增的 arctic_inference 依赖与本次 CI 变更无关，建议确认是否应该包含在该 PR 中。

[fastdeploy-bot]

🟡 建议 arctic_inference 依赖与本次 CI 变更主题无关。

本次 PR 是关于测试执行策略的优化，不应该引入新的运行时依赖。建议确认此依赖是否应该单独提交或从本次 PR 中移除。

[fastdeploy-bot]

🟡 建议 依赖版本不一致。

代码中 fastdeploy/spec_decode/suffix.py:46 提示安装 arctic-inference==0.1.2，但本次 PR 引入的是 0.1.3 版本，请确认版本一致性。

[fastdeploy-bot]

❓ 疑问 硬编码测试文件维护性较差。

9 个测试文件被硬编码在 Rule 5 中，后续新增高风险测试需要手动修改脚本。建议考虑更灵活的方式，如通过配置文件、环境变量或测试装饰器标记。

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@924690b). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #7268   +/-   ##
==========================================
  Coverage           ?   74.16%           
==========================================
  Files              ?      383           
  Lines              ?    53560           
  Branches           ?     8394           
==========================================
  Hits               ?    39722           
  Misses             ?    11149           
  Partials           ?     2689           

Flag	Coverage Δ
GPU	74.16% <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.