Skip to content

[Cherry-Pick][RL] Support GLM MTP RL Model (#6267)#6268

Merged
EmmonsCurse merged 11 commits intoPaddlePaddle:release/2.4from
Deleter-D:2.4_glm_rl
Feb 4, 2026
Merged

[Cherry-Pick][RL] Support GLM MTP RL Model (#6267)#6268
EmmonsCurse merged 11 commits intoPaddlePaddle:release/2.4from
Deleter-D:2.4_glm_rl

Conversation

@Deleter-D
Copy link
Collaborator

Motivation

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick,PR标题需遵循格式,在最开始加上[Cherry-Pick]标签,以及最后面加上原PR ID,例如[Cherry-Pick][CI] Add check trigger and logic(#5191)
N/A

Modifications

N/A

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
Copy link

paddle-bot bot commented Jan 29, 2026

Thanks for your contribution!

@codecov-commenter
Copy link

codecov-commenter commented Jan 29, 2026

Codecov Report

❌ Patch coverage is 15.85366% with 69 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/2.4@457b69f). Learn more about missing BASE report.

Files with missing lines Patch % Lines
fastdeploy/rl/rollout_model.py 17.14% 58 Missing ⚠️
fastdeploy/worker/gpu_model_runner.py 0.00% 4 Missing and 1 partial ⚠️
fastdeploy/model_executor/models/glm4_mtp.py 0.00% 4 Missing ⚠️
...ecutor/layers/attention/flash_mask_attn_backend.py 0.00% 2 Missing ⚠️
Additional details and impacted files
@@              Coverage Diff               @@
##             release/2.4    #6268   +/-   ##
==============================================
  Coverage               ?   56.97%           
==============================================
  Files                  ?      331           
  Lines                  ?    41363           
  Branches               ?     6305           
==============================================
  Hits                   ?    23565           
  Misses                 ?    15950           
  Partials               ?     1848           
Flag Coverage Δ
GPU 56.97% <15.85%> (?)

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.

@Deleter-D Deleter-D changed the title [Cherry-Pick][BugFix] Fix Issues in GLM MTP RL Model and Split Unit Tests (#6267) [Cherry-Pick][RL] Support GLM MTP RL Model (#6267) Feb 2, 2026
EmmonsCurse
EmmonsCurse previously approved these changes Feb 4, 2026
Copy link
Collaborator

@EmmonsCurse EmmonsCurse left a comment

Choose a reason for hiding this comment

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

LGTM for skip-coverage~

freeliuzc
freeliuzc previously approved these changes Feb 4, 2026
yuanlehome
yuanlehome previously approved these changes Feb 4, 2026
@EmmonsCurse EmmonsCurse merged commit ec15a0f into PaddlePaddle:release/2.4 Feb 4, 2026
15 of 20 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.

5 participants