# vllm-top
[](https://pypi.org/project/vllm-top/)
<p align="center">
<img src="demo/demo.gif" alt="Demo" width="600"/>
</p>
**vllm-top** is a Python package for monitoring and displaying metrics from the [vLLM](https://github.com/vllm-project/vllm) service. It provides a comprehensive dashboard to visualize both current state and historical performance, making it easy to track and analyze service behavior over time.
---
## 🚀 Features
- **Task State Visibility:** Instantly see GPU Cache Usage, Running and Waiting requests to help debug bottlenecks and improve throughput.
- **Minimalist Monitoring:** Lightweight dashboard that parses metrics directly from Prometheus.
- **Quick Setup:** No extra configuration — just pip install and run.
---
## 📦 Installation
Install via pip:
```bash
pip install vllm-top
```
---
## 🛠️ Usage
Start monitoring:
```bash
vllm-top
```
Change update interval (in seconds):
```bash
vllm-top --interval 5
```
Get a one-time snapshot:
```bash
vllm-top --snapshot
```
---
## 🤝 Contributing
Contributions are welcome! Please submit a pull request or open an issue for enhancements or bug fixes.
---
## 📄 License
Licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
---
## 📜 Changelog
See [CHANGELOG.md](CHANGELOG.md) for a detailed
Raw data
{
"_id": null,
"home_page": null,
"name": "vllm-top",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": null,
"keywords": "vllm, monitoring, metrics",
"author": null,
"author_email": "Yeok Tatt Cheah <yeokch@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/2a/8c/4411331293908f4546b68a8a2da82a3eb94a63cd3ae738875ff82e406ffa/vllm_top-0.1.2.tar.gz",
"platform": null,
"description": "# vllm-top\n\n[](https://pypi.org/project/vllm-top/)\n\n<p align=\"center\">\n <img src=\"demo/demo.gif\" alt=\"Demo\" width=\"600\"/>\n</p>\n\n**vllm-top** is a Python package for monitoring and displaying metrics from the [vLLM](https://github.com/vllm-project/vllm) service. It provides a comprehensive dashboard to visualize both current state and historical performance, making it easy to track and analyze service behavior over time.\n\n---\n\n## \ud83d\ude80 Features\n\n- **Task State Visibility:** Instantly see GPU Cache Usage, Running and Waiting requests to help debug bottlenecks and improve throughput.\n- **Minimalist Monitoring:** Lightweight dashboard that parses metrics directly from Prometheus.\n- **Quick Setup:** No extra configuration \u2014 just pip install and run.\n\n---\n\n## \ud83d\udce6 Installation\n\nInstall via pip:\n\n```bash\npip install vllm-top\n```\n\n---\n\n## \ud83d\udee0\ufe0f Usage\n\nStart monitoring:\n\n```bash\nvllm-top\n```\n\nChange update interval (in seconds):\n\n```bash\nvllm-top --interval 5\n```\n\nGet a one-time snapshot:\n\n```bash\nvllm-top --snapshot\n```\n\n---\n\n## \ud83e\udd1d Contributing\n\nContributions are welcome! Please submit a pull request or open an issue for enhancements or bug fixes.\n\n---\n\n## \ud83d\udcc4 License\n\nLicensed under the MIT License. See the [LICENSE](LICENSE) file for details.\n\n---\n\n## \ud83d\udcdc Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for a detailed\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A monitoring tool for vLLM metrics.",
"version": "0.1.2",
"project_urls": {
"Documentation": "https://github.com/yeok-c/vllm-top#readme",
"Homepage": "https://github.com/yeok-c/vllm-top",
"Issues": "https://github.com/yeok-c/vllm-top/issues",
"Repository": "https://github.com/yeok-c/vllm-top"
},
"split_keywords": [
"vllm",
" monitoring",
" metrics"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "cf30dc990f9ecd1fc1fe5220849a429480dadc4a04cdfc80b2cc050e73ffc95c",
"md5": "efa77a83fce0ec4fd0a0b02c41cfe746",
"sha256": "27b64ae88e33725a7f1d04879bf66932dadb2bb46ca422ea22b11e9b005024c4"
},
"downloads": -1,
"filename": "vllm_top-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "efa77a83fce0ec4fd0a0b02c41cfe746",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 8194,
"upload_time": "2025-08-03T16:59:44",
"upload_time_iso_8601": "2025-08-03T16:59:44.535159Z",
"url": "https://files.pythonhosted.org/packages/cf/30/dc990f9ecd1fc1fe5220849a429480dadc4a04cdfc80b2cc050e73ffc95c/vllm_top-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "2a8c4411331293908f4546b68a8a2da82a3eb94a63cd3ae738875ff82e406ffa",
"md5": "ff1e65b5f07e4a28b410b973e49ac5a6",
"sha256": "0a9e9e9e21cf3ce5752f9685aa02a7d5fb690647fb9eca918cacd4da7e464ccd"
},
"downloads": -1,
"filename": "vllm_top-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "ff1e65b5f07e4a28b410b973e49ac5a6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 9335,
"upload_time": "2025-08-03T16:59:45",
"upload_time_iso_8601": "2025-08-03T16:59:45.619508Z",
"url": "https://files.pythonhosted.org/packages/2a/8c/4411331293908f4546b68a8a2da82a3eb94a63cd3ae738875ff82e406ffa/vllm_top-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-03 16:59:45",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "yeok-c",
"github_project": "vllm-top#readme",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "prometheus_client",
"specs": []
},
{
"name": "requests",
"specs": []
}
],
"lcname": "vllm-top"
}
JSON
