Metadata-Version: 2.4
Name: vllm-cluster-manager
Version: 0.2.2
Summary: Deploy, manage, and monitor vLLM instances across a GPU cluster from a single web dashboard.
Author-email: Marc Schlichting <mschl@stanford.edu>
License: MIT
Project-URL: Homepage, https://github.com/sisl/VLLMClusterManager
Keywords: vllm,llm,gpu,cluster,inference,deployment
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown

# vLLM Cluster Manager

Deploy, manage, and monitor vLLM instances across a GPU cluster from a single web dashboard.

## Quick Start

```bash
pip install vllm-cluster-manager
```

**On each GPU node (satellite):**

```bash
vllm-cluster-manager client install
vllm-cluster-manager client start
```

**On the management server (host):**

```bash
vllm-cluster-manager host install
vllm-cluster-manager host start
```

Then open the dashboard at `http://<host-ip>:5173` to deploy and monitor models across your cluster.

## Features

- Web dashboard for deploying and managing vLLM models across multiple GPU nodes
- Automatic vLLM version management with isolated per-deployment virtual environments
- Live GPU utilization metrics and deployment status monitoring
- Consul-based automatic node discovery
- Support for custom pip packages and vLLM plugins
