[Metax][CI] update metax ci

[Tryorish]

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 调整 Metax CI 中 ERNIE-4.5-VL 28B 用例的张量并行配置，将测试从 2 卡 TP 改为 1 卡 TP，以适配单卡运行场景。

Changes:

• 将 tests/metax_ci/test_ernie_28b_vl.py 中 tensor_parallel_size 从 2 改为 1。
• 需要补充 PR 描述中的 Motivation / Modifications，当前仍是模板内容。
• 本次看起来是 CI 配置变更，通常不需要更新用户文档，但建议在 PR 描述中说明无需文档变更。

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | ci_status_monitor | 2026-05-14 15:40:30

CI报告基于以下代码生成（30分钟更新一次）:

• PR commit: 3e34a28
• Merge base: cb2d7c0 (branch: develop)
• 查看完整 Diff
• CI 详情

---

1 任务总览

✅ 所有 Required 任务均已通过，建议合并。

总执行（rerun次数）	总任务	✅ 通过	❌ 失败	⏳ 运行中	⏸️ 等待中	跳过
42(0)	42	27	1	1	1	12

---

2 任务状态汇总

2.1 Required任务 : 2/10 通过

必选任务阻塞合并，失败需优先处理。

状态	任务	耗时	根因	修复建议	日志	重跑
✅	其余 2 个必选任务通过（Approval、Pre Commit）	-	-	-	-	-

注：另有 8 个 Required 任务通过 bypass/skip-CI 跳过执行（非失败，不阻塞合并）。

2.2 可选任务 — 25/32 通过

可选任务不阻塞合并，失败仅供参考。

状态	任务	耗时	日志	重跑
❌	Check PR Template	16s	Job	-
⏳	Trigger Jenkins for PR（CI_METAX）	运行中	Job	-
⏸️	CI_HPU	等待中	Job	-
✅	其余 25 个可选任务通过	-	-	-

---

3 失败详情（仅 required）

无 required 失败任务。

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@6e149e3). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #7812   +/-   ##
==========================================
  Coverage           ?   63.15%           
==========================================
  Files              ?      461           
  Lines              ?    64152           
  Branches           ?     9828           
==========================================
  Hits               ?    40516           
  Misses             ?    20860           
  Partials           ?     2776           

Flag	Coverage Δ
GPU	72.27% <ø> (?)
XPU	7.12% <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.

[EmmonsCurse]

/skip-ci ci_iluvatar
/skip-ci ci_hpu
/skip-ci build_xpu
/skip-ci build_gpu

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | pr_review | 2026-05-14 15:38:05

📋 Review 摘要

PR 概述：在 Metax CI 测试中取消注释 graph_optimization_config，显式禁用 CUDAGraph 并将 graph_opt_level 设为 0。
变更范围：tests/metax_ci/
影响面 Tag：[Metax] [CI]

📝 PR 规范检查

PR 描述所有段落（Motivation / Modifications / Usage or Command / Accuracy Tests）均为空（仅含占位符注释），Checklist 全部未勾选，不符合描述模板规范。

标题建议（可直接复制）：

• [Metax][CI] Enable graph_optimization_config in ERNIE-28B-VL Metax CI test

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

## Motivation
在 Metax CI 的 ERNIE-28B-VL 测试中，`graph_optimization_config` 参数此前被注释掉，导致图优化配置采用默认值。本次变更将其显式启用，设置 `use_cudagraph=False` 和 `graph_opt_level=0`，以提升 Metax 硬件上 CI 测试的稳定性。

## Modifications
- `tests/metax_ci/test_ernie_28b_vl.py`：取消注释 `graph_optimization_config={"use_cudagraph": False, "graph_opt_level": 0}`，在测试 setUp 时显式禁用 CUDAGraph 及图优化。

## Usage or Command
N/A

## Accuracy Tests
N/A（CI 配置变更，不影响模型输出精度）

## 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.
- [x] Add unit tests. Please write the reason in this PR if no unit tests.
- [x] 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.

问题

未发现阻塞性问题。

总体评价

变更本身简洁合理，显式禁用 CUDAGraph 可提升 Metax CI 稳定性。建议作者补全 PR 描述后合入。