Skip to content

Conversation

@xiaoxiaohehe001
Copy link
Collaborator

@xiaoxiaohehe001 xiaoxiaohehe001 commented Jan 7, 2026

Motivation

  • Support redundant expert for eplb
  • 启动服务时添加
    --eplb-config '{"redundant_experts_num": 32, "redundant_expert_async_load_model_shmem_size_gb": 10}'
  • [Cherry-Pick][Feature] Support redundant expert for eplb ([Feature] Support redundant expert for eplb #5918)

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 Jan 7, 2026

Thanks for your contribution!

@codecov-commenter
Copy link

codecov-commenter commented Jan 7, 2026

Codecov Report

❌ Patch coverage is 16.66667% with 10 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/online/20251131@7aea651). Learn more about missing BASE report.

Files with missing lines Patch % Lines
fastdeploy/model_executor/load_weight_utils.py 0.00% 4 Missing ⚠️
fastdeploy/entrypoints/engine_client.py 0.00% 2 Missing ⚠️
fastdeploy/worker/worker_process.py 33.33% 2 Missing ⚠️
fastdeploy/model_executor/layers/moe/moe.py 50.00% 0 Missing and 1 partial ⚠️
fastdeploy/worker/experts_manager.py 0.00% 1 Missing ⚠️
Additional details and impacted files
@@                    Coverage Diff                     @@
##             release/online/20251131    #5923   +/-   ##
==========================================================
  Coverage                           ?   58.46%           
==========================================================
  Files                              ?      320           
  Lines                              ?    39204           
  Branches                           ?     5918           
==========================================================
  Hits                               ?    22921           
  Misses                             ?    14443           
  Partials                           ?     1840           
Flag Coverage Δ
GPU 58.46% <16.66%> (?)

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.

@xiaoxiaohehe001 xiaoxiaohehe001 changed the title [Cherry-Pick][BugFix] Support redundant expert for eplb (#5918) [Cherry-Pick][Feature] Support redundant expert for eplb (#5918) Jan 8, 2026
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Copilot encountered an error and was unable to review this pull request. You can try again by re-requesting a review.

Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

Copilot reviewed 10 out of 10 changed files in this pull request and generated 5 comments.

self.num_hidden_layers = num_hidden_layers

self.num_replicas = self.num_expert + self.redundant_experts_num
self.num_nodes = max(ep_size // 8, 1)
Copy link
Collaborator

Choose a reason for hiding this comment

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

这个改动的目的是啥?那如果是单机呢

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

这部分修改就是为了适配单机/多机,测试来看num_nodes=8能够保证初始化专家排布的正确性

Copy link
Collaborator

@gongshaotian gongshaotian left a comment

Choose a reason for hiding this comment

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

LGTM

Copy link
Collaborator

@RichardWooSJTU RichardWooSJTU left a comment

Choose a reason for hiding this comment

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

LGTM

@yuanlehome yuanlehome merged commit c2ad0a9 into PaddlePaddle:release/online/20251131 Jan 9, 2026
11 of 16 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.

6 participants