Skip to content

Conversation

@liyonghua0910
Copy link
Collaborator

@liyonghua0910 liyonghua0910 commented Jan 4, 2026

Motivation

当前在开启 PrefixCaching 时,会伴随启动一个 CacheTransferManager 进程,用于 CPU-GPU 的缓存块交换。而负责 CPU-GPU 的缓存交换的进程只是在开启 CPU Cache 时才需要,而非 PrefixCaching 所需。

Modifications

  • 修改 CacheTransferManager 进程的启动条件为,开启 CPU Cache 时才启动。
  • 同步修改了 clear/update 接口的判断逻辑

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
Copy link

paddle-bot bot commented Jan 4, 2026

Thanks for your contribution!

@codecov-commenter
Copy link

codecov-commenter commented Jan 4, 2026

Codecov Report

❌ Patch coverage is 0% with 34 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/2.4@2a71e42). Learn more about missing BASE report.

Files with missing lines Patch % Lines
fastdeploy/entrypoints/engine_client.py 0.00% 24 Missing ⚠️
fastdeploy/cache_manager/prefix_cache_manager.py 0.00% 8 Missing and 2 partials ⚠️
Additional details and impacted files
@@              Coverage Diff               @@
##             release/2.4    #5859   +/-   ##
==============================================
  Coverage               ?   58.86%           
==============================================
  Files                  ?      329           
  Lines                  ?    40773           
  Branches               ?     6209           
==============================================
  Hits                   ?    24003           
  Misses                 ?    14895           
  Partials               ?     1875           
Flag Coverage Δ
GPU 58.86% <0.00%> (?)

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 liyonghua0910 changed the title [fix] temporarily forbid cpu cache in update/clear api [Cherry-Pick] [KVCache] launch cache transfer processes only if hierarchical cache or kv cache storage is enabled (#5871) Jan 5, 2026
@Jiang-Jia-Jun Jiang-Jia-Jun merged commit f3ebd64 into PaddlePaddle:release/2.4 Jan 6, 2026
13 of 18 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants