[Cherry-Pick][RL] Add clear_graph_opt_backend for glm4_mtp (#7378)

[Deleter-D]

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!

[PaddlePaddle-bot]

🤖 AI Code Review | 2026-04-16 21:15 CST

📋 Review 摘要

PR 概述：为 Glm4MTPForCausalLM 模型添加 clear_grpah_opt_backend 方法，用于清理 CUDA Graph 优化后端，Cherry-Pick 自 #7378。
变更范围：model_executor/models/glm4_mtp.py
影响面 Tag：Models Graph Optimization

📝 PR 规范检查

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

描述建议（可直接复制）：

Motivation: Cherry-Pick from #7378. 为 GLM4 MTP 模型补充 clear_grpah_opt_backend 方法，使其支持 CUDA Graph 的清理与重捕获，与其他模型（qwen3、deepseek_v3、glm4_moe 等）保持一致。

Modifications: 在 Glm4MTPForCausalLM 类中新增 clear_grpah_opt_backend 方法，调用内部 self.model 的同名方法完成清理。

问题

未发现阻塞性问题。

总体评价

变更内容简洁、符合项目现有模式。新增的 clear_grpah_opt_backend 方法实现与 qwen3、deepseek_v3、glm4_moe、ernie4_5_moe 等模型完全一致，底层调用的是 decorator.py 中 @support_graph_optimization 装饰器注入的同名方法。代码无误，可正常合入。

[codecov-commenter]

Codecov Report

❌ Patch coverage is 50.00000% with 1 line in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (release/2.5@12e4fff). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/model_executor/models/glm4_mtp.py	50.00%	1 Missing ⚠️

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.5    #7443   +/-   ##
==============================================
  Coverage               ?   68.97%           
==============================================
  Files                  ?      390           
  Lines                  ?    54389           
  Branches               ?     8579           
==============================================
  Hits                   ?    37513           
  Misses                 ?    14182           
  Partials               ?     2694           

Flag	Coverage Δ
GPU	68.97% <50.00%> (?)

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.