[Others] Exit to ensure no residual processes (cpu cache & dp)

[CSWYF3634076]

Motivation

优雅退出，保证无残留进程 （启动服务具有CPU cache功能，ctrl+c关闭时会残留cache_transfer_manager进程）

Modifications

start_data_parallel_service在结束后调用expert_service._exit_sub_services()清理cache_transfer_manager进程

Usage or Command

CUDA_VISIBLE_DEVICES=0,2 \
ENABLE_V1_KVCACHE_SCHEDULER=1 \
python /root/paddlejob/workspace/env_run/output/wangyafeng/myGithub/FastDeploy/fastdeploy/entrypoints/openai/api_server.py \
--model /root/paddlejob/workspace/env_run/output/wangyafeng/models/Qwen3-VL-30B-A3B-Instruct \
--data-parallel-size 2 \
--workers 8 \
--port 8801 \
--engine-worker-queue-port 8902 \
--cache-queue-port 8903 \
--gpu-memory-utilization 0.9 \
--max-model-len 8192 \
--max-num-seqs 32 \
--swap-space 50 \
--graph-optimization-config '{"use_cudagraph":false}' \
--load-choices dummy \
--limit-mm-per-prompt '{"image": 100, "video": 100}'

main分支
启动后ctrl+c，有cache_transfer_manager.py的残留进程

PR
启动后ctrl+c，无残留进程

Accuracy Tests

no

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!

[codecov-commenter]

Codecov Report

❌ Patch coverage is 42.85714% with 4 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@6563b83). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/engine/expert_service.py	50.00%	2 Missing and 1 partial ⚠️
fastdeploy/cache_manager/prefix_cache_manager.py	0.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #6377   +/-   ##
==========================================
  Coverage           ?   68.23%           
==========================================
  Files              ?      391           
  Lines              ?    52245           
  Branches           ?     8145           
==========================================
  Hits               ?    35647           
  Misses             ?    13991           
  Partials           ?     2607           

Flag	Coverage Δ
GPU	68.23% <42.85%> (?)

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.

[liyonghua0910]

只有 EP 场景会杀不干净吗