[Cherry-Pick][RL]Remove extra argument from per_token_quant calls in deepgemm MoE backend, fix #6850

[zhanghonggeng]

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.

[paddle-bot]

Thanks for your contribution!

[Copilot]

Pull request overview

该 PR 旨在修复 DeepGEMM MoE 后端中对 per_token_quant 自定义 GPU op 的错误调用方式，移除多余的入参以匹配当前算子签名，避免运行时因参数不匹配而报错。

Changes:

• 在 DeepGEMM MoE 后端两处 per_token_quant 调用中移除多余的第三个参数。
• 统一 FD_USE_PHI_FP8_QUANT=False 分支下的量化调用方式，仅传递 (input, block_size)。

[Copilot]

该 PR 标题作为 Cherry-Pick 仍未满足仓库约定格式：需要在标题末尾追加原 develop PR 编号（例如 ...(#xxxx)）。当前标题缺少原始 PR ID，可能触发 CI 的 Cherry-Pick 校验失败。

[Copilot]

PR 描述的 Motivation/Modifications/Accuracy Tests 等关键字段目前为空，且 Checklist 中未解释为何不补充单测与精度结果。该改动涉及量化/后端调用（可能影响运行与数值路径），建议补充：1) 修改动机与影响范围；2) 至少给出相关单测/命令或说明为何无需；3) 如适用提供精度对比结果。

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (release/2.5@7af95be). Learn more about missing BASE report.

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.5    #7258   +/-   ##
==============================================
  Coverage               ?   68.51%           
==============================================
  Files                  ?      390           
  Lines                  ?    54405           
  Branches               ?     8577           
==============================================
  Hits                   ?    37276           
  Misses                 ?    14435           
  Partials               ?     2694           

Flag	Coverage Δ
GPU	68.51% <ø> (?)

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.

[fastdeploy-bot]

🤖 AI Code Review | 2026-04-09

📋 Review 摘要

PR 概述：修复 deepgemm MoE backend 中 per_token_quant 函数调用时传入多余的第三个参数

变更范围：fastdeploy/model_executor/layers/moe/fused_moe_deepgemm_backend.py

影响面 Tag：[RL]

📝 PR 规范检查

PR 描述中的 Motivation 和 Modifications 部分为空，建议补充：

描述模板（可直接复制）：

## Motivation

`per_token_quant` 函数签名只接受两个参数（`input` 和 `block_size`），但代码中传入了第三个参数导致运行时报错。

## Modifications

移除 `per_token_quant` 函数调用中的第三个参数：
- `m_grouped_fp8_gemm_nt_contiguous_custom_python_op` 函数中的调用
- `apply_ep_prefill` 方法中的调用

问题

未发现阻塞性问题。

总体评价

✅ 修改正确。已验证 per_token_quant 函数签名（来自 cpp_extensions.cc）只接受 input 和 block_size 两个参数，其他调用点（测试文件、triton_backend 等）也都使用两个参数。建议补充 PR 描述以提高可追溯性。