# Vllm Multimodal Open Issue Analyzer

> Fetch and organize multimodal-related open issues from vllm-project/vllm. Categorizes issues by problem type (Bug, Feature Request, Performance, CUDA Graph, EPD disaggregation, Prefix Caching, ViT/visual encoder, Video, Audio/Speech, specific VL models, etc.) and generates a structured Markdown report saved to the skill's ./outputs directory. Use when the user wants to collect, search, analyze, o…

- **Type:** Skill
- **Install:** `agentstack add skill-shen-shanshan-vllm-dev-skills-vllm-multimodal-open-issue-analyzer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [shen-shanshan](https://agentstack.voostack.com/s/shen-shanshan)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [shen-shanshan](https://github.com/shen-shanshan)
- **Source:** https://github.com/shen-shanshan/vllm-dev-skills/tree/master/skills/vllm-multimodal-open-issue-analyzer
- **Website:** https://zhuanlan.zhihu.com/p/2031696581678866733

## Install

```sh
agentstack add skill-shen-shanshan-vllm-dev-skills-vllm-multimodal-open-issue-analyzer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# vllm 多模态 Open Issues 分析

## 工作流

1. 运行 `scripts/fetch_multimodal_issues.py`
2. 脚本自动抓取、去重、分类，生成 Markdown 报告
3. 报告默认保存至 `/outputs/vllm_multimodal_issues_.md`
4. 告知用户报告路径及 issue 总数

## 运行脚本

```bash
python3 scripts/fetch_multimodal_issues.py
```

可选参数：

| 参数 | 说明 | 示例 |
|------|------|------|
| `--token` | GitHub token（有 gh CLI 时不需要） | `--token ghp_xxx` |
| `--output-dir` | 自定义报告输出目录 | `--output-dir /tmp/reports` |
| `--keywords` | 追加额外关键词（逗号分隔） | `--keywords "DeepSeek-VL,Kimi"` |
| `--stdout` | 输出到终端而非文件 | `--stdout` |

## 搜索关键词覆盖范围

**通用术语**: multimodal, multi-modal, VLM, vision language, image input

**VL 模型**: Qwen-VL/2/2.5, LLaVA, InternVL, MiniCPM-V, Phi-3/4-vision, PaliGemma, Florence, Pixtral, CogVLM, LLaMA-Vision, Idefics

**Omni/音频**: Qwen-Omni/2/2.5, audio, whisper, speech

**视频**: video understanding, video input, temporal

**特性关键词**: ViT, visual encoder, cuda graph, EPD, prefix caching, image token, image patch

## 问题类型分类逻辑

脚本对每个 issue 的标题、label、body（前 500 字符）做关键词匹配，归入以下类别（一个 issue 可属于多个类别）：

- Bug / 错误报告
- Feature Request / 功能请求
- Performance / 性能问题
- CUDA Graph / 计算图
- EPD / 编解码分离
- Prefix Caching / 前缀缓存
- ViT / 视觉编码器
- Video Multimodal / 视频多模态
- Audio / Speech / 音频语音
- VL Model: Qwen-VL系列 / Qwen-Omni系列 / LLaVA系列 / InternVL系列 / 其他模型
- Image Token / 输入处理
- Compatibility / 兼容性
- Documentation / 文档
- 其他 / Other

## 报告结构

生成的 Markdown 报告包含三部分：

1. **Issue 总览**（表格）：编号、标题、作者、创建日期、Labels
2. **按问题类型分类**：每个类别列出匹配 issue（含链接、创建日期）
3. **分类统计**：各类别 issue 数量汇总表

## 认证说明

- **有 gh CLI**（推荐）：自动使用，无速率限制
- **无 gh CLI，有 token**：使用 `--token`
- **无认证**：搜索批次间自动等待 6 秒，避免触发 GitHub 10 req/min 限制

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [shen-shanshan](https://github.com/shen-shanshan)
- **Source:** [shen-shanshan/vllm-dev-skills](https://github.com/shen-shanshan/vllm-dev-skills)
- **License:** Apache-2.0
- **Homepage:** https://zhuanlan.zhihu.com/p/2031696581678866733

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-shen-shanshan-vllm-dev-skills-vllm-multimodal-open-issue-analyzer
- Seller: https://agentstack.voostack.com/s/shen-shanshan
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.