Skip to content

[RL] Clear Requests status of R3#6569

Merged
yuanlehome merged 1 commit intoPaddlePaddle:release/2.4from
gongshaotian:r3_fix_rb_2.4
Mar 2, 2026
Merged

[RL] Clear Requests status of R3#6569
yuanlehome merged 1 commit intoPaddlePaddle:release/2.4from
gongshaotian:r3_fix_rb_2.4

Conversation

@gongshaotian
Copy link
Collaborator

@gongshaotian gongshaotian commented Feb 28, 2026

Motivation

Fix the bug caused by the failure to clear the status of over-issued requests in the Replay Buffer scenario.

TODO:

  • Cherry-pick to develop, release/2.5

Modifications

  1. clear_requests() func

Usage or Command

Pass

Accuracy Tests

Pass

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 Feb 28, 2026

Thanks for your contribution!

@codecov-commenter
Copy link

Codecov Report

❌ Patch coverage is 20.00000% with 4 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/2.4@dc095ea). Learn more about missing BASE report.

Files with missing lines Patch % Lines
...model_executor/layers/moe/routing_indices_cache.py 33.33% 2 Missing ⚠️
fastdeploy/worker/gpu_model_runner.py 0.00% 2 Missing ⚠️
Additional details and impacted files
@@              Coverage Diff               @@
##             release/2.4    #6569   +/-   ##
==============================================
  Coverage               ?   56.38%           
==============================================
  Files                  ?      333           
  Lines                  ?    42357           
  Branches               ?     6444           
==============================================
  Hits                   ?    23885           
  Misses                 ?    16603           
  Partials               ?     1869           
Flag Coverage Δ
GPU 56.38% <20.00%> (?)

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.

@yuanlehome yuanlehome merged commit 7d76fd4 into PaddlePaddle:release/2.4 Mar 2, 2026
14 of 18 checks passed
gongshaotian added a commit that referenced this pull request Mar 11, 2026
)

* [RL]  R3  Support Fully Async and PrefixCache (#6314)

* [RL] R3 Fix the bug for determining the end of a request (#6388)

* 1.move put routing to postprocess 2.extend async put task queue

* fix speculate eos token bug

* delete code

* delete code

* refine code

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

* [RL] Clear Requests status of R3 (#6569)

* [RL]Perf: Optimize batch delete prefix and fused put in R3 (#6604)

* Optimizate delete batch and fused put

* refine code

* refine code

* refine code

* Support suspend r3

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
yuanlehome pushed a commit that referenced this pull request Mar 12, 2026
* cherry-pick  Support Fully Async and PrefixCache step 1

* copy routing_indices_cache.py from 2.4

* cherry-pick [RL] R3 Fix the bug for determining the end of a request (#6388)

* cherry-pick [RL] Clear Requests status of R3 (#6569)

* delete code

* fix rename bug

* fix status shape bug

* fix ci
yuanlehome pushed a commit that referenced this pull request Mar 19, 2026
* cherry-pick  Support Fully Async and PrefixCache step 1

* copy routing_indices_cache.py from 2.4

* cherry-pick [RL] R3 Fix the bug for determining the end of a request (#6388)

* cherry-pick [RL] Clear Requests status of R3 (#6569)

* fix bug

* [RL]Perf: Optimize batch delete prefix and fused put in R3 (#6604)

* Optimizate delete batch and fused put

* refine code

* refine code

* refine code

* Support suspend r3

* [RL] Fix R3 Empty bug with TP=1 (#6777)

* fix bug

* fix ci bug

* fix routing mask

* delete check len
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