[Cherry-Pick][BugFix] Fix import compatibility for paddlefleet.ops and paddlefleet_ops(#7873)

[liuruyan]

Motivation

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick，PR标题需遵循格式，在最开始加上[Cherry-Pick]标签，以及最后面加上原PR ID，例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

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.

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | pr_review | 2026-05-21 12:01:33

📋 Review 摘要

PR 概述：Cherry-Pick 修复因 paddlefleet 包名变更导致的 EP / FP8 加载失败 Bug，兼容新旧两种包路径。
变更范围：fastdeploy/model_executor/layers/moe/ep.py、fastdeploy/model_executor/layers/quantization/fp8_utils.py
影响面 Tag：[OP] [Quantization]

问题

级别	文件	概述
🟡 建议	ep.py	裸 except: 会吞掉 SystemExit/KeyboardInterrupt，建议改为 except ImportError:
🟡 建议	fp8_utils.py	同上，load_deep_gemm 中裸 except: 建议改为 except ImportError:
📝 PR 规范	—	标题缺少官方 Tag；描述体必填段落均为空

ep.py（load_deep_ep 内层 try/except，新增行约第 48 行）与 fp8_utils.py（load_deep_gemm 内层 try/except，新增行约第 50 行）存在裸 except: 捕获问题；根据 checklist §C"异常处理吞掉异常"表层信号项触发。

📝 PR 规范检查

存在两处问题：① 标题格式缺少官方 Tag（Cherry-Pick 格式要求 [Cherry-Pick][Tag]）；② PR 描述中 Motivation / Modifications / Usage or Command / Accuracy Tests 四个必填段落均为空或仅占位符。

标题建议（可直接复制）：

• [Cherry-Pick][BugFix] Fix ce bug because of paddlefleet_ops(#7873)

PR 描述建议（可直接复制）：

## Motivation
兼容 paddlefleet 包路径的两种形式（`paddlefleet.ops.deep_ep` / `paddlefleet_ops.deep_ep` 和 `paddlefleet.ops.deep_gemm` / `paddlefleet_ops.deep_gemm`），修复因 PaddleFleet 包名变更导致的 EP 和 DeepGEMM 加载失败问题。

## Modifications
- `fastdeploy/model_executor/layers/moe/ep.py`：删除模块级别无效的 `try_import(["paddlefleet.ops"])`；`load_deep_ep` 中优先尝试 `import paddlefleet.ops.deep_ep`，失败则回退到 `import paddlefleet_ops.deep_ep`。
- `fastdeploy/model_executor/layers/quantization/fp8_utils.py`：`try_import` 参数增加 `"paddlefleet_ops"` 备选包；`load_deep_gemm` 中优先尝试 `import paddlefleet.ops.deep_gemm`，失败则回退到 `import paddlefleet_ops.deep_gemm`。

## Usage or Command
N/A

## Accuracy Tests
N/A

## Checklist

- [x] 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.
- [x] 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.
- [x] 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.

总体评价

兼容性修复思路正确，try_import 双包名传参和内层 try/except 回退均能实现新旧路径兼容。建议将两处裸 except: 收窄为 except ImportError:，并补全 PR 描述中的必填段落。

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | ci_status_monitor | 2026-05-21 14:11:47

CI报告基于以下代码生成（30分钟更新一次）:

• PR commit: d7ea046
• Merge base: b5c8290 (branch: release/2.6)
• 查看完整 Diff
• CI 详情

---

1 任务总览

极简 PR，本次仅修改 paddlefleet.ops / paddlefleet_ops 导入兼容逻辑。当前 Required 任务无失败、无运行中、无等待中；但有 1 个任务处于跳过状态，请确认该跳过符合预期。Optional 失败不阻塞合并，仅供参考。

总执行（rerun次数）	总任务	✅ 通过	❌ 失败	⏳ 运行中	⏸️ 等待中	跳过
54(18)	36	31	4	0	0	1

2 任务状态汇总

日志列说明：失败任务直接使用 CI 工具生成的日志链接；运行中任务使用 Job 链接。

2.1 Required任务 : 9/10 通过

必选任务阻塞合并，失败需优先处理。当前无 required 失败任务。

状态	任务	耗时	根因	修复建议	日志	重跑
⏭️	Run FastDeploy Unit Tests and Coverage / run_tests_with_coverage	-	跳过	确认本次跳过符合预期	-	-
✅	其余 9 个必选任务通过	-	-	-	-	-

2.2 可选任务 — 22/26 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	14m52s	Job	-
❌	Check PR Template	15s	Job	-
❌	CI_HPU	1h7m	Job	-
❌	Trigger Jenkins for PR	1m4s	Job	-
✅	其余 22 个可选任务通过	-	-	-

---

3 失败详情（仅 required）

无 required 失败任务。按策略，本次未对 optional 失败任务做深度分析。

[codecov-commenter]

Codecov Report

❌ Patch coverage is 11.11111% with 8 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/2.6@b5c8290). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/model_executor/layers/moe/ep.py	0.00%	4 Missing ⚠️
...oy/model_executor/layers/quantization/fp8_utils.py	20.00%	4 Missing ⚠️

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.6    #7874   +/-   ##
==============================================
  Coverage               ?   72.34%           
==============================================
  Files                  ?      381           
  Lines                  ?    54225           
  Branches               ?     8473           
==============================================
  Hits                   ?    39227           
  Misses                 ?    12233           
  Partials               ?     2765           

Flag	Coverage Δ
GPU	72.34% <11.11%> (?)

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.