Skip to content

Conversation

@EmmonsCurse
Copy link
Collaborator

Motivation

CP from #5725
In CI jobs, workspace cleanup and GPU memory release may occasionally fail, for example with errors like rm: Directory not empty causing the pipeline to exit unexpectedly.
This issue mainly occurs in the temporary execution environments used by PR CI jobs, where leftover files, concurrent operations may prevent a single cleanup attempt from succeeding, impacting CI stability.

Modifications

  1. Strengthened the repository cleanup logic by using rm -rf ${REPO_NAME}* to ensure all possible residual directories are removed
  2. Increase test timeout for ERNIE-4.5-VL-28B-A3B-Thinking
  3. Fix image build to use the correct upstream artifacts
  4. Added stricter cleanup and validation steps before downloading and extracting artifacts to avoid interference from a dirty workspace
  5. Improved the overall robustness of the CI script to reduce failures caused by transient environment issues

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.

@CLAassistant
Copy link

CLAassistant commented Dec 26, 2025

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
10 out of 11 committers have signed the CLA.

✅ EmmonsCurse
✅ rainyfly
✅ kxz2002
✅ kevincheng2
✅ ckl117
✅ yuanlehome
✅ liyonghua0910
✅ Wanglongzhi2001
✅ Deleter-D
✅ tianhaodongbd
❌ yubaoku


yubaoku seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
You have signed the CLA already but the status is still pending? Let us recheck it.

@paddle-bot
Copy link

paddle-bot bot commented Dec 26, 2025

Thanks for your contribution!

…dlePaddle#5775)

* disable chunked_mm_input in ernie5

* cp_disable_mm_chunked

* update test case

* update code
@codecov-commenter
Copy link

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (release/2.4@9a8e215). Learn more about missing BASE report.

Additional details and impacted files
@@              Coverage Diff               @@
##             release/2.4    #5790   +/-   ##
==============================================
  Coverage               ?   59.05%           
==============================================
  Files                  ?      328           
  Lines                  ?    40731           
  Branches               ?     6204           
==============================================
  Hits                   ?    24053           
  Misses                 ?    14798           
  Partials               ?     1880           
Flag Coverage Δ
GPU 59.05% <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.

ZhangYulongg
ZhangYulongg previously approved these changes Dec 26, 2025
rainyfly and others added 13 commits December 29, 2025 09:52
…tion (PaddlePaddle#5758) (PaddlePaddle#5802)

* support process_response_dict async initial commit

* fixbug

* add unit test

* optimize
…dle#5819)

* [Speculative Decoding] Fix attn_mask_offset for multi-step MTP in mixed and PD-split modes (PaddlePaddle#5738)

* fix attn_mask_offset in mtp with multi-step and pd-split-mode

* fix xpu operater register

* update pmtp multi-step mtp strategy in d-split -mode

* add note

* fix xpu register

* fix entropy bugs

* Revert "[Speculative Decoding] Fix attn_mask_offset for multi-step MTP in mixed and PD-split modes (PaddlePaddle#5738)"

This reverts commit ba0d35a.

* fix ut

* fix

---------

Co-authored-by: freeliuzc <[email protected]>
…addle#5578)

* [CI] Remove test_metrics.py due to incompatible forced merge
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.