[Cherry-Pick][OP]Unify MoE op with moe_permute path for bf16 GLM (#7164)

[fxyfxy777]

💡 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)

Motivation

使用 Paddle 官方的 moe_permute/moe_unpermute 算子替代自定义算子，简化代码并提高可维护性。

Modifications

1. 修改 deepgemm_preprocess.cu kernel，新增 cumsum 输出
2. 新增 FD_USE_PHI_MOE_PERMUTE 环境变量控制的代码路径
3. 当 FD_USE_PHI_MOE_PERMUTE=1 且 quant_type=w16a16 时使用 Paddle 算子

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]

Thanks for your contribution!

[fastdeploy-bot]

🤖 AI Code Review | 2026-04-09 17:04 CST

📋 Review 摘要

PR 概述：Cherry-pick PR #7164，使用 Paddle 官方的 moe_permute/moe_unpermute 算子替代自定义算子，简化 MoE 层代码并提高可维护性。

变更范围：

• custom_ops/gpu_ops/moe/deepgemm_preprocess.cu - 新增 cumsum 输出支持
• fastdeploy/model_executor/layers/moe/fused_moe_cutlass_backend.py - 新增 FD_USE_PHI_MOE_PERMUTE 环境变量控制的代码路径
• fastdeploy/model_executor/layers/moe/fused_moe_deepgemm_backend.py - 更新函数调用签名
• tests/layers/test_fused_moe_cutlass_backend.py - 新增真实算子测试

影响面 Tag：[OP] [Models]

问题

级别	文件	概述
🟡 建议	tests/layers/test_fused_moe_cutlass_backend.py:825	测试中定义了未使用的追踪变量

总体评价

PR 实现质量良好，CUDA kernel 的模板参数设计合理，Python 层与 C++ 层接口一致。新增的测试用例覆盖了 apply_tp 和 apply_ep_prefill 两个路径，包括 noaux_tc 和非 noaux_tc 分支。发现一个小的测试代码优化点，不阻塞合入。

[fastdeploy-bot]

🟡 建议 dispatch_called 变量定义后从未被更新，导致此断言始终为 True。

虽然测试通过 monkeypatch 对 moe_expert_dispatch 抛出 AssertionError 已经确保了该函数不会被调用（否则测试会失败），但这个断言本身是冗余的，可以移除以提高代码清晰度。

建议：

# 删除未使用的变量和断言
permute_called = {"v": False}
original_permute = paddle.nn.functional.moe_permute

# ... spy_permute 定义 ...

# 删除这行：assert not dispatch_called["v"], "moe_expert_dispatch must not be called"

[codecov-commenter]

Codecov Report

❌ Patch coverage is 80.64516% with 6 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/2.6@849eb3d). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
...l_executor/layers/moe/fused_moe_cutlass_backend.py	79.31%	3 Missing and 3 partials ⚠️

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.6    #7279   +/-   ##
==============================================
  Coverage               ?   73.89%           
==============================================
  Files                  ?      376           
  Lines                  ?    52915           
  Branches               ?     8255           
==============================================
  Hits                   ?    39103           
  Misses                 ?    11085           
  Partials               ?     2727           

Flag	Coverage Δ
GPU	73.89% <80.64%> (?)

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.