← Back to list

dsh-model-manager

DeepSeek Harness Models & Providers Low risk

Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.

DSH Web 视图中的本地 LLM 推理服务控制面板:服务注册表与健康检查/停止控制、llama.cpp / SGLang / vLLM 命名参数 profile(保存前做 KV/显存校验)、GPU 探测与 tok/s 测速。

How to install

DeepSeek Harness dsh plugin add dsh-model-manager

About

dsh-model-manager **语言 / Language: 中文 | English** 本地 LLM 推理服务的「总控台」——DSH(DeepSeek Harness)插件。 为什么 本地同时跑几个推理服务(llama.cpp / SGLang / vLLM)时,参数散落在终端历史和笔记本里:这个模型该配哪套 -c / -np?显存到底够不够?哪个框架在这张卡上能起? 装好本插件,这些答案都在一个面板里: 之前:翻终端历史、手动算 KV、等 OOM 才知道配置超了; 之后:服务注册表一眼看清谁在哪张卡上跑,参数 Profile 保存前就校验显存,一键测速对比 tok/s。 快速开始 **前提**:DSH(带 web)+ pnpm;GPU 检测需要 python3(缺失时自动回退 nvidia-smi)。 bash cd ~/.dsh/profiles/web # 你的 DSH web profile 目录 pnpm add github:Ansonfishing/dsh-model-manager 然后在 package.json 的 dsh.profile.bundles 数组里加上 "dsh-model-manager",重启 dsh。会话视图出现「模型管理」tab,就好了。 功能 **服务注册表**——登记本地推理服务(端口、框架、模型、GPU),健康检查实时显示…

Recommendation signals

49 Tool quality · Based on stars, downloads, maintenance, security and docs
User interest · Adjusted by in-site views, install copies and download clicks
49 Overall
0views
0unique visitors
0install copies
0download clicks
0outbound clicks

Meta

License
MIT
Language
JavaScript
GitHub stars
0
mo. downloads
Last push
2026-08-29
Created
2026-08-28

Links

Basic safety check

Findings
None
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics
dashboard, deepseek-harness, developer-tools, dsh, dsh-plugin, gpu, inference-server, llama-cpp, local-inference, local-llm, plugin, react, sglang, vllm, vram

Related plugins

DeepSeek HarnessClaude CodeCodex New
Score80

dsh-plugin-subscriptions

V1ki/dsh-plugin-subscriptions

Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.

☆ 305 ↓ 5.8K Models & Providers
DeepSeek Harness
Score78

dsh-commandcode-provider

Mars-Sea/dsh-commandcode-provider

Unofficial Command Code LLM provider: registers a `commandcode` route with a live model catalog and reasoning-effort support.

☆ 133 ↓ 7.2K Models & Providers
DeepSeek HarnessCodex
Score76

dsh-codex-connect

franksong2702/dsh-codex-connect

Connect ChatGPT OAuth and OpenAI Codex models to DeepSeek Harness, with opt-in search and image tools.

☆ 69 ↓ 9.4K Models & Providers
Claude Code
Score74

claude-code-router

musistudio/claude-code-router

One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.

☆ 37.0K ↓ – Models & Providers