Skip to content

Conversation

@zhupengyang
Copy link
Collaborator

@zhupengyang zhupengyang commented Oct 30, 2025

Motivation

  • 把ep+tp的组网从model层下放到op层
  • 修复eb45 moe组网代码。因为tp的token划分是不均匀的,token_num比较小可能导致id靠后的卡索引错误
  • xpu相关
    • 支持tp+ep
    • 支持空跑只跑moe

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 Oct 30, 2025

Thanks for your contribution!

@zhupengyang zhupengyang force-pushed the ep_tp_100 branch 2 times, most recently from 78f88ae to 296eca1 Compare October 30, 2025 11:35
@zhupengyang zhupengyang changed the title support ep+tp at backend op layer support ep+tp at op layer Oct 30, 2025
@zhupengyang zhupengyang force-pushed the ep_tp_100 branch 3 times, most recently from 07087cc to 7ded145 Compare October 31, 2025 07:15
yuanlehome
yuanlehome previously approved these changes Nov 3, 2025
Copy link
Collaborator

@yuanlehome yuanlehome left a comment

Choose a reason for hiding this comment

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

LGTM

@EmmonsCurse EmmonsCurse merged commit 2fd254e into PaddlePaddle:develop Nov 5, 2025
27 of 34 checks passed
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.

4 participants