Install
Inside DeepSeek Harness, with dsh-market
dsh plugin --profile web add dshmarket
Or from the command line
dsh plugin --profile web add github:173787247/dsh-wsl-llamacpp
Installing runs third-party code with your own permissions — it can read your files, use your credentials and reach the network. Review the source first, and pin a commit (github:owner/repo#sha) when you can.
README
Languages: 中文（首页） · English (this file)
OpenAI-compatible client for llama.cpp / Unsloth Desktop (default :8080).
| Version | 0.1.0 |
| Kit | Optional companion to dsh-wsl-kit; not in install.sh |
Install
dsh plugin --profile web add github:173787247/dsh-wsl-llamacpp
Batch link (optional): bash dsh-wsl-kit/scripts/link-linux-plugins.sh
Tools
| Tool | Role |
|---|---|
llama_status |
reachability + model ids |
llama_chat |
chat completions |
Config
baseUrl / defaultModel / timeoutMs
Reuse existing GGUF servers. Env: DSH_LLAMA_BASE, DSH_LLAMA_MODEL.
Compatibility
| Field | Value |
|---|---|
| Plugin | dsh-wsl-llamacpp 0.1.0 |
| Minimum dsh | ≥ 0.1.2 (web UI one-shot ?token= on Windows relay :3081) |
| Latest verified | See dsh-wsl-kit Compatibility (currently 0.2.0-rc.2) — single source of truth for the suite |
| Kit set | optional (not in install.sh / KIT_SET=daily by default) |
License
MIT
Comments
Comments live in GitHub Discussions. Sign in with GitHub to post or react.