[CI][XPU] add mtp case

[plusNew001]

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

此PR为XPU CI添加了MTP（Multi-Token Prediction，多令牌预测）模式的测试用例，用于验证ERNIE-4.5-21B-A3B-Paddle模型在推测解码配置下的功能。

主要变更：

• 新增MTP模式测试用例，配置包括wint4量化和4路张量并行
• 实现基于OpenAI API的非流式对话测试
• 验证模型响应内容的正确性

[Copilot]

导入语句的顺序不符合Python最佳实践。json标准库导入应该放在第三方库（openai, pytest）之前，conftest本地导入应该最后。建议按照以下顺序组织导入：

1. 标准库（json）
2. 第三方库（openai, pytest）
3. 本地模块（conftest）

Suggested change

	import openai
	import pytest
	from conftest import get_model_path, get_port_num, print_logs_on_failure, start_server
	import json
	import json
	import openai
	import pytest
	from conftest import get_model_path, get_port_num, print_logs_on_failure, start_server

[Copilot]

f-string格式化字符串中不需要额外的花括号。应该直接使用 json.dumps(spec_config) 而不是 f"{json.dumps(spec_config)}"，因为json.dumps已经返回字符串类型。

Suggested change

	f"{json.dumps(spec_config)}",
	json.dumps(spec_config),

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ plusNew001
❌ root

---

root seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@dbedb07). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5537   +/-   ##
==========================================
  Coverage           ?   60.74%           
==========================================
  Files              ?      329           
  Lines              ?    41140           
  Branches           ?     6271           
==========================================
  Hits               ?    24991           
  Misses             ?    14258           
  Partials           ?     1891           

Flag	Coverage Δ
GPU	60.74% <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.