Skip to content

[BugFix] fix all reduce fusion accurate issue#7923

Open
BingooYang wants to merge 1 commit into
PaddlePaddle:developfrom
BingooYang:fix_allreduce_acc_dev
Open

[BugFix] fix all reduce fusion accurate issue#7923
BingooYang wants to merge 1 commit into
PaddlePaddle:developfrom
BingooYang:fix_allreduce_acc_dev

Conversation

@BingooYang
Copy link
Copy Markdown
Contributor

Motivation

修复同时开启 export FD_USE_PHI_RMSNORM=1 和 --enable-flashinfer-allreduce-fusion 引起的精度问题

Modifications

开启 export FD_USE_PHI_RMSNORM=1 环境变量,RMSNorm其中一个分支适配 all reduce fusion

Usage or Command

NA

Accuracy Tests

done

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
Copy Markdown

paddle-bot Bot commented May 25, 2026

Thanks for your contribution!

@PaddlePaddle-bot
Copy link
Copy Markdown

PaddlePaddle-bot commented May 25, 2026

🤖 Paddle-CI-Agent | ci_status_monitor | 2026-05-26 00:14:21

CI报告基于以下代码生成(30分钟更新一次):


1 任务总览

所有 required 任务已通过,建议通过;当前有 2 个 optional 任务失败、1 个 optional workflow 等待中,仅供参考,不阻塞合并。

总执行(rerun次数) 总任务 ✅ 通过 ❌ 失败 ⏳ 运行中 ⏸️ 等待中 跳过
41(0) 41 38 2 0 1 0

2 任务状态汇总

日志列说明:失败任务直接使用 CI 日志链接;optional 失败不阻塞合并,本次不做深度分析。

2.1 Required任务 : 10/10 通过

必选任务阻塞合并,失败需优先处理。

状态 任务 耗时 根因 修复建议 日志 重跑
其余 10 个必选任务通过 - - - - -

2.2 可选任务 — 28/31 通过

可选任务不阻塞合并,失败仅供参考。

状态 任务 耗时 日志 重跑
Run iluvatar Tests / run_iluvatar_cases 1m51s Job -
Trigger Jenkins for PR 1m53s Job -
⏸️ CI_HPU - - -
其余 28 个可选任务通过 - - -

3 失败详情(仅 required)

无 required 失败任务。


备注

  • PR 变更文件:fastdeploy/model_executor/layers/normalization.pytests/layers/trtllm_allreduce_rms_fusion.py
  • 已抽查变更上下文:RMSNorm proxy 分支新增 allreduce fusion 路径,新增测试覆盖 fused/fallback 分支;主 Required 测试 Run FastDeploy Unit Tests and Coverage / run_tests_with_coverage 已通过。

@codecov-commenter
Copy link
Copy Markdown

codecov-commenter commented May 25, 2026

Codecov Report

❌ Patch coverage is 75.00000% with 2 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@f23586e). Learn more about missing BASE report.

Files with missing lines Patch % Lines
fastdeploy/model_executor/layers/normalization.py 75.00% 0 Missing and 2 partials ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             develop    #7923   +/-   ##
==========================================
  Coverage           ?   63.80%           
==========================================
  Files              ?      467           
  Lines              ?    64969           
  Branches           ?     9963           
==========================================
  Hits               ?    41451           
  Misses             ?    20713           
  Partials           ?     2805           
Flag Coverage Δ
GPU 72.88% <75.00%> (?)
XPU 7.07% <0.00%> (?)

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.

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