[BugFix] Fix import compatibility for paddlefleet.ops and paddlefleet_ops

[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 12:01:24

📋 Review 摘要

PR 概述：修复 paddlefleet 包路径变更导致的 deep_ep 和 deep_gemm 导入兼容性问题，新增对 paddlefleet.ops 新路径的支持，同时保留对旧路径 paddlefleet_ops 的回退
变更范围：model_executor/layers/moe/ep.py、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:48	裸 except: 应改为 except ImportError:，避免误吞关键异常
🟡 建议	fp8_utils.py:50	裸 except: 应改为 except ImportError:，避免误吞关键异常
📝 PR 规范	—	标题缺少官方 [Tag]，PR 描述各段均为占位符未填写

📝 PR 规范检查

标题无官方 [Tag]；PR 描述中 Motivation / Modifications / Usage or Command / Accuracy Tests 各段内容均为空/占位符，Checklist 条目全部未勾选。

标题建议（可直接复制）：

• [BugFix] Fix import compatibility for paddlefleet.ops and paddlefleet_ops

PR 描述建议（可直接复制，必须复刻 checklist §D2 模板的完整结构）：

## Motivation
修复 `paddlefleet` 包路径变更导致的兼容性问题：新版 `paddlefleet` 将 ops 子模块路径从 `paddlefleet_ops.deep_ep`/`paddlefleet_ops.deep_gemm` 迁移至 `paddlefleet.ops.deep_ep`/`paddlefleet.ops.deep_gemm`，旧路径导致 ImportError。本 PR 在 `ep.py` 和 `fp8_utils.py` 中同时兼容两种路径，优先尝试新路径，失败时回退到旧路径。

## Modifications
- `fastdeploy/model_executor/layers/moe/ep.py`：移除模块级 `try_import(["paddlefleet.ops"])` 调用；在 `load_deep_ep()` 内新增内层 try/except，优先 `import paddlefleet.ops.deep_ep`，回退 `import paddlefleet_ops.deep_ep`
- `fastdeploy/model_executor/layers/quantization/fp8_utils.py`：更新模块级 `try_import` 同时检测 `paddlefleet.ops` 和 `paddlefleet_ops`；在 `load_deep_gemm()` 内新增内层 try/except，优先 `import paddlefleet.ops.deep_gemm`，回退 `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.
- [ ] 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.

总体评价

兼容性修复逻辑清晰，能正确处理包路径迁移场景。建议将两处裸 except: 改为 except ImportError: 以避免误吞 KeyboardInterrupt 等关键异常；PR 标题和描述规范需同步补充。

[PaddlePaddle-bot]

🟡 建议 裸 except: 捕获范围过宽

当前 except: 会捕获所有异常（包括 KeyboardInterrupt、SystemExit），若 paddlefleet.ops 已安装但因非导入原因（如内部初始化错误）抛出非 ImportError 异常，将被静默吞掉并错误地回退到旧路径，导致难以排查的问题。

建议修复方式：

try:
    import paddlefleet.ops.deep_ep as deep_ep  # type: ignore
except ImportError:
    import paddlefleet_ops.deep_ep as deep_ep  # type: ignore

[PaddlePaddle-bot]

🟡 建议 裸 except: 捕获范围过宽

同 ep.py 问题：当前 except: 捕获所有异常，若 paddlefleet.ops 包存在但初始化时抛出非 ImportError 异常，将被静默吞掉并错误回退。

建议修复方式：

try:
    import paddlefleet.ops.deep_gemm as deep_gemm
except ImportError:
    import paddlefleet_ops.deep_gemm as deep_gemm

[codecov-commenter]

Codecov Report

❌ Patch coverage is 11.11111% with 8 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@c9e1bf5). 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             @@
##             develop    #7873   +/-   ##
==========================================
  Coverage           ?   63.58%           
==========================================
  Files              ?      462           
  Lines              ?    64490           
  Branches           ?     9887           
==========================================
  Hits               ?    41006           
  Misses             ?    20705           
  Partials           ?     2779           

Flag	Coverage Δ
GPU	72.71% <11.11%> (?)
XPU	7.11% <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.

[EmmonsCurse]

LGTM～ Skip coverage check as it mainly relies on tests with paddlefleet.