Skip to content

Conversation

@cmcamdy
Copy link
Collaborator

@cmcamdy cmcamdy commented Dec 11, 2025

Motivation

发现mix状态下,draft从base model中获得的hidden states顺序是经过adjust排序过的。该顺序下当同时存在query插入+一条query在base中结束时会发生draft model获取 hidden states错位,这样会导致当前step draft model输出的token质量下降

💡 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)

Modifications

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 Dec 11, 2025

Thanks for your contribution!

@codecov-commenter
Copy link

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@c3aaa7e). Learn more about missing BASE report.

Additional details and impacted files
@@            Coverage Diff             @@
##             develop    #5513   +/-   ##
==========================================
  Coverage           ?   60.27%           
==========================================
  Files              ?      329           
  Lines              ?    41116           
  Branches           ?     6261           
==========================================
  Hits               ?    24784           
  Misses             ?    14443           
  Partials           ?     1889           
Flag Coverage Δ
GPU 60.27% <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.

Copy link
Collaborator

@hong19860320 hong19860320 left a comment

Choose a reason for hiding this comment

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

LGTM

@cmcamdy cmcamdy merged commit 3c1f7b8 into PaddlePaddle:develop Dec 12, 2025
15 of 17 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.

3 participants