[xpu] fix interrupt error

[zhupengyang]

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]

🤖 Paddle-CI-Agent | ci_status_monitor | 2026-05-15 10:36:49

CI报告基于以下代码生成（30分钟更新一次）:

• PR commit: 7de938c
• Merge base: c2df4c6 (branch: develop)
• 查看完整 Diff
• CI 详情

---

1 任务总览

⏳ Required 任务运行中：2 个必选任务仍在执行，请等待完成后再合并。当前已通过 2/4 必选任务。

总执行（rerun次数）	总任务	✅ 通过	❌ 失败	⏳ 运行中	⏸️ 等待中	跳过
21(0)	21	14	1	4	0	2

2 任务状态汇总

2.1 Required任务：2/4 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
⏳	xpu_4cards_case_test / run_xpu_4cards_cases	-	运行中	-	Job	-
⏳	xpu_8cards_case_test / run_xpu_8cards_cases	-	运行中	-	Job	-
✅	其余 2 个必选任务通过	-	-	-	-	-

2.2 可选任务 — 12/17 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	15s	Job	-
⏳	xpu_unit_test / run_xpu_unit_test	-	Job	-
⏳	Trigger Jenkins for PR	-	Job	-
✅	其余 12 个可选任务通过	-	-	-

---

3 失败详情（仅 required）

无 required 失败任务。

[codecov-commenter]

Codecov Report

❌ Patch coverage is 0% with 3 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@c2df4c6). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/worker/xpu_model_runner.py	0.00%	3 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff            @@
##             develop   #7805   +/-   ##
=========================================
  Coverage           ?   7.12%           
=========================================
  Files              ?     462           
  Lines              ?   64274           
  Branches           ?    9851           
=========================================
  Hits               ?    4577           
  Misses             ?   59608           
  Partials           ?      89           

Flag	Coverage Δ
XPU	7.12% <0.00%> (?)

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.

[EmmonsCurse]

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

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | pr_review | 2026-05-15 10:24:44

📋 Review 摘要

PR 概述：XPU ModelRunner 在非 EP 模式下 num_tokens 为 0 时提前退出，修复 interrupt 错误
变更范围：fastdeploy/worker/xpu_model_runner.py
影响面 Tag：[XPU] [BugFix]

📝 PR 规范检查

标题含非标准 [not merge] 前缀且 [xpu] 大小写不规范；PR 描述各 section 未填写实际内容。

标题建议（可直接复制）：

• [XPU][BugFix] Fix interrupt error when num_tokens is 0

PR 描述建议（可直接复制）：

## Motivation

XPU ModelRunner 在非 Expert Parallel 模式下，当 `ids_remove_padding` 的 token 数为 0 时，直接调用 model forward 会触发 interrupt 错误。通过在 `execute_model` 中添加提前退出逻辑，避免以空 batch 执行推理。

## Modifications

- `fastdeploy/worker/xpu_model_runner.py`：在 `execute_model` 的 `padding_cudagraph_inputs()` 调用之后，增加 `num_tokens <= 0` 的 early-return 判断；EP 模式下即使 token 为 0 仍需参与集合通信，故仅在非 EP 模式下触发。

## Usage or Command

N/A

## Accuracy Tests

N/A

## 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.

问题

级别	文件	概述
📝 PR 规范	—	标题含非标准 [not merge] 前缀、[xpu] 大小写不规范；描述各 section 未填写实际内容
❓ 疑问	fastdeploy/worker/xpu_model_runner.py:1304	num_tokens <= 0 中 < 0 分支不可达，建议改为 == 0 以提高语义准确性

总体评价

修复逻辑正确：非 EP 模式下 token 数为 0 时提前返回，与已有 EP 模式注释保持一致，改动小风险低。请在合入前补充 PR 描述并修正标题格式。