[BugFix] support moe for sm103

[BingooYang]

Motivation

支持moe sm103编译

Modifications

支持sm103编译

Usage or Command

no

Accuracy Tests

no

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 | 2026-04-08 13:56 CST

📋 Review 摘要

PR 概述：支持 SM103 架构的 MoE GEMM 编译
变更范围：custom_ops/gpu_ops/cutlass_kernels/moe_gemm/
影响面 Tag：[OP]

问题

级别	文件	概述
🔴 Bug	fused_moe_gemm_kernels_template.h:712	编译时与运行时架构检查范围不一致

总体评价

PR 目标是支持 SM103 架构编译，但存在编译时检查（__CUDA_ARCH__ < 1100）和运行时检查（sm_ < 104）范围不一致的问题。建议统一两处的架构范围，确保编译和运行时行为一致。

[fastdeploy-bot]

🔴 Bug 架构范围不一致：编译时检查 (__CUDA_ARCH__ < 1100) 支持到 SM109，但运行时检查 (sm_ < 104) 只支持到 SM103。

这会导致在 SM104-SM109 架构上编译的代码运行时抛出错误。

原因分析：

• __CUDA_ARCH__ 宏格式为 major*100 + minor，1100 对应 SM110
• sm_ 通过 getSMVersion() 获取，格式为 major*10 + minor，104 对应 SM104

建议修复方式：
统一架构范围，有两种选择：

1. 如果目标是支持到 SM103：

   • 编译时改为 < 1040
   • 运行时保持 < 104

2. 如果目标是支持到 SM109：

   • 编译时保持 < 1100
   • 运行时改为 < 110

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@c529c2a). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #7238   +/-   ##
==========================================
  Coverage           ?   73.91%           
==========================================
  Files              ?      383           
  Lines              ?    53510           
  Branches           ?     8377           
==========================================
  Hits               ?    39550           
  Misses             ?    11195           
  Partials           ?     2765           

Flag	Coverage Δ
GPU	73.91% <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.

[zoooo0820]

LGTM