[CI] Remove flashinfer cache cleanup to reduce unit test runtime

[EmmonsCurse]

Motivation

The flashinfer cache cleanup step was introducing unnecessary overhead during unit test execution.
Since the cache removal is not required for test correctness, it leads to increased test runtime without providing additional value.

Modifications

• Removed the explicit cleanup of the flashinfer cache directory (/root/.cache/flashinfer) in the distributed test.
• Eliminated subprocess-based cache deletion to streamline test startup and improve overall CI efficiency.

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.

[paddle-bot]

Thanks for your contribution!

[EmmonsCurse]

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

[PaddlePaddle-bot]

🤖 AI Code Review | 2026-04-18 20:59 CST

📋 Review 摘要

PR 概述：移除分布式测试中不必要的 flashinfer cache 清理步骤，以减少 CI 运行时间
变更范围：tests/layers/test_trtllm_allreduce_rms_fusion.py
影响面 Tag：CI

问题

未发现阻塞性问题。

总体评价

变更简洁安全。删除的 cache 清理逻辑（rm -rf /root/.cache/flashinfer）不影响测试正确性，flashinfer 库会自行管理其编译缓存。删除后 os、subprocess 等 import 仍被其他代码使用，无残留 dead import。LGTM。

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@b2aca6c). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #7476   +/-   ##
==========================================
  Coverage           ?   74.19%           
==========================================
  Files              ?      398           
  Lines              ?    54987           
  Branches           ?     8616           
==========================================
  Hits               ?    40800           
  Misses             ?    11453           
  Partials           ?     2734           

Flag	Coverage Δ
GPU	74.19% <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.