Skip to content

Conversation

@rainyfly
Copy link
Collaborator

@rainyfly rainyfly commented Jan 19, 2026

Motivation

优化在 EP 并行下的首 token 问题:

  1. 在 forward 结束后调度发下一班车。
  2. 发车时没有请求使用空请求同步。

Modifications

None

Usage or Command

None

Accuracy Tests

None

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 19, 2026

Thanks for your contribution!

@rainyfly rainyfly changed the title [Optimize] optimize ttft for EP [Optimize][Cherry-pick] optimize ttft for EP(#6098) Jan 19, 2026
@codecov-commenter
Copy link

codecov-commenter commented Jan 20, 2026

Codecov Report

❌ Patch coverage is 52.38095% with 20 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/online/20251131@e29272c). Learn more about missing BASE report.

Files with missing lines Patch % Lines
fastdeploy/worker/worker_process.py 53.84% 5 Missing and 7 partials ⚠️
fastdeploy/engine/common_engine.py 22.22% 7 Missing ⚠️
fastdeploy/scheduler/dp_scheduler.py 85.71% 0 Missing and 1 partial ⚠️
Additional details and impacted files
@@                    Coverage Diff                     @@
##             release/online/20251131    #6085   +/-   ##
==========================================================
  Coverage                           ?   57.36%           
==========================================================
  Files                              ?      324           
  Lines                              ?    39388           
  Branches                           ?     5943           
==========================================================
  Hits                               ?    22594           
  Misses                             ?    14968           
  Partials                           ?     1826           
Flag Coverage Δ
GPU 57.36% <52.38%> (?)

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.

@Jiang-Jia-Jun Jiang-Jia-Jun merged commit 26486a6 into PaddlePaddle:release/online/20251131 Jan 21, 2026
12 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