[Cherry-Pick][KVCache] Support request-level prefix cache disable(#7854)

[kevincheng2]

Motivation

将 develop PR #7854 同步到 release/2.6，支持请求级禁用 prefix caching。部分请求需要跳过 prefix cache 的匹配、写入和释放复用路径，以避免污染或复用全局缓存；默认值保持 False，继续遵循全局 prefix caching 配置。

Modifications

• OpenAI Completion/ChatCompletion 请求新增 disable_prefix_caching 参数，并贯通到内部 Request 序列化/反序列化。
• ResourceManager 和 ResourceManagerV1 在请求级禁用时跳过 prefix cache 匹配、cache block 更新、输出/存储写入和 prefix tree 释放路径。
• 补充 legacy ResourceManager、ResourceManagerV1、Request/OpenAI protocol 单测。
• 更新中英文 online serving 请求参数文档。

Usage or Command

# 单测
/root/paddlejob/inference-public/chengyanfu/.venv/py310/bin/python -m pytest \
  tests/engine/test_request.py \
  tests/engine/test_resource_manager.py \
  tests/v1/test_resource_manager_v1.py -q

请求示例：

client.chat.completions.create(
    model="null",
    messages=[{"role": "user", "content": "hello"}],
    extra_body={"disable_prefix_caching": True},
)

Accuracy Tests

不涉及模型计算逻辑或算子变更，未执行精度测试。

Checklist

• Add at least a tag in the PR title.
• 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!

[codecov-commenter]

Codecov Report

❌ Patch coverage is 77.41935% with 7 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/2.6@41d44d6). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/engine/sched/resource_manager_v1.py	70.83%	0 Missing and 7 partials ⚠️

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.6    #7855   +/-   ##
==============================================
  Coverage               ?   72.95%           
==============================================
  Files                  ?      381           
  Lines                  ?    54231           
  Branches               ?     8476           
==============================================
  Hits                   ?    39562           
  Misses                 ?    11891           
  Partials               ?     2778           

Flag	Coverage Δ
GPU	72.95% <77.41%> (?)

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.

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | pr_review | 2026-05-19 19:03:05

📋 Review 摘要

PR 概述：新增请求级 prefix caching 禁用开关，允许单个请求跳过全局 prefix cache 的匹配、写入和释放路径。
变更范围：engine/request.py、engine/resource_manager.py、engine/sched/resource_manager_v1.py、entrypoints/openai/protocol.py、文档
影响面 Tag：[KVCache] [APIServer] [Engine]

问题

未发现阻塞性问题。

📝 PR 规范检查

标题格式 [Cherry-Pick][KVCache] ... (#7854) 符合 Cherry-Pick 规范；描述包含 Motivation / Modifications / Usage or Command / Accuracy Tests / Checklist 全部段落，结构合规。✓

总体评价

实现思路清晰，_enable_prefix_cache_for_request 辅助方法统一替换散落的 enable_prefix_cache 直接判断，代码改动具有一致性。序列化链路（protocol.py → request.py to_dict/from_dict/from_generic_request）完整；单测覆盖了默认值、传播、bypass 等关键路径。整体可合入。

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | ci_status_monitor | 2026-05-19 19:52:00

CI报告基于以下代码生成（30分钟更新一次）:

• PR commit: 627ea21
• Merge base: 41d44d6 (branch: release/2.6)
• 查看完整 Diff
• CI 详情

---

1 任务总览

所有 required 任务均已通过 ✅，PR 可合并。有 2 个可选任务失败（不阻塞合并）。

总执行（rerun次数）	总任务	✅ 通过	❌ 失败	⏳ 运行中	⏸️ 等待中	跳过
36(0)	36	33	2	0	1	0

2 任务状态汇总

2.1 Required任务 : 10/10 通过

必选任务阻塞合并，失败需优先处理。

状态	任务	耗时	根因	修复建议	日志	重跑
✅	其余 10 个必选任务通过	-	-	-	-	-

2.2 可选任务 — 23/26 通过

可选任务不阻塞合并，失败仅供参考。

状态	任务	耗时	日志	重跑
❌	Run iluvatar Tests / run_iluvatar_cases	1m29s	Job	-
❌	Trigger Jenkins for PR	50m10s	Job	-
⏸️	CI_HPU	-	-	-
✅	其余 23 个可选任务通过	-	-	-

---

3 失败详情（仅 required）

无