⚡ Bolt: Optimize single element list appends

[google-labs-jules]

💡 What: Replaced instances of .extend([item]) with .append(item) in multiple files.
🎯 Why: Using .extend([item]) incurs memory overhead by allocating a new single-element list and is computationally slower (~2.5x) than calling .append(item) directly.
📊 Impact: Reduces memory allocation overhead during list operations and improves execution speed slightly for frequent list updates.
🔬 Measurement: Verified the code syntactically using py_compile. Tests weren't fully run due to missing complex dependencies like PaddlePaddle, but the change is a mechanically safe equivalent substitution.

---

PR created automatically by Jules for task 578869324811361848 started by @ZeyuChen

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[paddle-bot]

Thanks for your contribution!

[PaddlePaddle-bot]

🤖 AI Code Review | 2026-04-16

📋 Review 摘要

PR 概述：将 .extend([item]) 替换为 .append(item) 以优化列表操作性能
变更范围：数据编码器、输出处理器、模型运行器（GPU/Metax）
影响面 Tag：[DataProcessor] [Metax]

📝 PR 规范检查

PR 标题和描述不符合项目规范，请按以下方式修改：

标题建议（可直接复制）：

• [Optimization] Optimize single element list appends

描述模板（可直接复制）：

## Motivation
Using `.extend([item])` incurs memory overhead by allocating a new single-element list and is computationally slower (~2.5x) than calling `.append(item)` directly.

## Modifications
Replaced instances of `.extend([item])` with `.append(item)` in multiple files:
- `fastdeploy/input/encodings/ernie_encoding.py`
- `fastdeploy/input/ernie4_5_vl_processor/process.py`
- `fastdeploy/output/token_processor.py`
- `fastdeploy/worker/gpu_model_runner.py`
- `fastdeploy/worker/metax_model_runner.py`

问题

级别	文件	概述
🟡 建议	标题	使用 ⚡ emoji 而非标准 Tag [Optimization]
🟡 建议	描述	未使用 Motivation/Modifications 标准模板

总体评价

代码变更本身正确且安全，是有效的性能优化。所有 .extend([single_item]) → .append(single_item) 的替换都是语义等价的，能够减少内存分配和提升性能。请按建议调整 PR 规范后合并。