dsh-local-llm-controller

Plugins in this repository

• dsh-local-llm-controllerv2.0.0✓

  DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and DSH provider registration with names derived from the chosen model file.

  package.json

  package.json

  dsh.bundle.patch

  cordis.patch.yml

  Official core packages (2)

  • @deepseek-ai/dsh-client-locale^0.1.0-rc.7shared
  • @deepseek-ai/dsh-client-ui-settings^0.1.0-rc.7shared

Paths are pinned to commit e1f21ede9fb5

Overview

为DSH接入本地大模型能力：在「设置→插件」页一键启停本地 llama.cpp 大模型（35B/9B，视觉×文本×快速/长上下文），卡片内配置、一条命令安装、自动注册，装完即用。 | start/stop a local llama.cpp llama-server right from Settings → Plugins, with Qwen3.6-35B / Qwen3.5-9B (vision × text, fast × long-context) as session models — card config, one-command install, auto-registered.