# dsh-model-manager

> Manage local LLM inference servers in DSH: GPU registry, parameter profiles, VRAM validation, and tok/s benchmarks for llama.cpp, SGLang, and vLLM

## Metadata

- Author: [@Ansonfishing](https://github.com/Ansonfishing)
- Repo: <https://github.com/Ansonfishing/dsh-model-manager>
- Stars: 0
- Added: 2026-08-28T16:00:00.000Z

## Install

```bash
dsh plugin --profile web add dsh-model-manager
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-model-manager](https://deepseek-plugin.org/plugins/Ansonfishing/dsh-model-manager)