Skip to content

Conversation

@juncaipeng
Copy link
Collaborator

@juncaipeng juncaipeng commented Nov 28, 2025

Motivation

pd 分离下 pd 支持不同的 tp_size

Modifications

  • rdma 传输库
  • cache messager模块
  • router 收集 tp_size 信息

Usage or Command

不变

Accuracy Tests

参考单侧

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.

Copilot AI review requested due to automatic review settings November 28, 2025 07:19
@paddle-bot
Copy link

paddle-bot bot commented Nov 28, 2025

Thanks for your contribution!

Copilot finished reviewing on behalf of juncaipeng November 28, 2025 07:19
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot encountered an error and was unable to review this pull request. You can try again by re-requesting a review.

Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 12 out of 13 changed files in this pull request and generated 13 comments.


You can also share your feedback on Copilot code review for a chance to win a $100 gift card. Take the survey.

ddchenhao66
ddchenhao66 previously approved these changes Dec 1, 2025
Copy link
Collaborator

@ddchenhao66 ddchenhao66 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@codecov-commenter
Copy link

codecov-commenter commented Dec 1, 2025

Codecov Report

❌ Patch coverage is 20.40816% with 39 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@8aec3ac). Learn more about missing BASE report.

Files with missing lines Patch % Lines
fastdeploy/cache_manager/cache_messager.py 9.09% 20 Missing ⚠️
fastdeploy/router/utils.py 33.33% 10 Missing ⚠️
fastdeploy/router/router.py 0.00% 6 Missing ⚠️
...he_manager/transfer_factory/rdma_cache_transfer.py 33.33% 2 Missing ⚠️
fastdeploy/splitwise/splitwise_connector.py 66.66% 1 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             develop    #5296   +/-   ##
==========================================
  Coverage           ?   59.63%           
==========================================
  Files              ?      324           
  Lines              ?    39629           
  Branches           ?     5961           
==========================================
  Hits               ?    23631           
  Misses             ?    14122           
  Partials           ?     1876           
Flag Coverage Δ
GPU 59.63% <20.40%> (?)

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.

@Jiang-Jia-Jun Jiang-Jia-Jun merged commit 0925d44 into PaddlePaddle:develop Dec 1, 2025
14 of 18 checks passed
)

def connect(self, ip, port):
def connect(self, ip, port, tp_size):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里是不是加个默认值=0

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants