Skip to content

Conversation

@xiaoxiaohehe001
Copy link
Collaborator

@xiaoxiaohehe001 xiaoxiaohehe001 commented Nov 23, 2025

Motivation

Modifications

  • 支持在 eplb 下 fp8 格式加载权重
  • 修复 eplb 加载时传入 list 报错情况

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 Nov 23, 2025

Thanks for your contribution!

@codecov-commenter
Copy link

codecov-commenter commented Nov 23, 2025

Codecov Report

❌ Patch coverage is 5.55556% with 17 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@b9e76f1). Learn more about missing BASE report.

Files with missing lines Patch % Lines
fastdeploy/worker/worker_process.py 0.00% 6 Missing ⚠️
fastdeploy/eplb/async_expert_loader.py 0.00% 4 Missing ⚠️
fastdeploy/eplb/experts_manager.py 25.00% 3 Missing ⚠️
...l_executor/layers/moe/fused_moe_cutlass_backend.py 0.00% 2 Missing ⚠️
..._executor/layers/moe/fused_moe_deepgemm_backend.py 0.00% 2 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             develop    #5178   +/-   ##
==========================================
  Coverage           ?   57.67%           
==========================================
  Files              ?      317           
  Lines              ?    38456           
  Branches           ?     5765           
==========================================
  Hits               ?    22178           
  Misses             ?    14502           
  Partials           ?     1776           
Flag Coverage Δ
GPU 57.67% <5.55%> (?)

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.

kevincheng2
kevincheng2 previously approved these changes Nov 24, 2025
state_dicts = load_tensor_from_shm_mem(self.experts_manager.tensor_infos, mmap_infos[MODEL_MAIN_NAME], logger)
rank_expert_list, logical_to_physical_map, expert_count = self.experts_manager.get_ep_rank_to_expert_id_list()
self.worker.get_model().redundant_table_manger.update_expert_rank_table(
self.worker.get_model().ernie.redundant_table_manger.update_expert_rank_table(
Copy link
Collaborator

Choose a reason for hiding this comment

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

能把redundant_table_manger从ernie组网里移出来吗,这看起来eplb跟ernie强行绑定了,它应该是一个公共组件吧

@Jiang-Jia-Jun Jiang-Jia-Jun merged commit 95f3c8c into PaddlePaddle:develop Nov 24, 2025
13 of 18 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.

5 participants