Sessions & Messages

dsh-wsl-vllm

173787247/dsh-wsl-vllm · ★ 1

173787247

DeepSeek Harness WSL plugin: vLLM OpenAI-compatible status + chat (Docker/local serving).

Manifest details

Static manifest checks report declarations only; they are not compatibility or security review.

安装

dsh plugin --profile web add 'github:173787247/dsh-wsl-vllm#66e46698a07718d9cecc0dcb303e4d721e570901'

GitHub 源码安装：首次需按提示配置 allowBuilds 构建授权后重试

For install and environment setup, plus plugin development tutorials, see DSH community docs ↗

Table of contents

Languages: 中文（首页） · English (this file)

OpenAI-compatible vLLM client (default :8000).


Version	0.1.0
Kit	Optional companion to dsh-wsl-kit; not in `install.sh`

dsh plugin --profile web add github:173787247/dsh-wsl-vllm

Batch link (optional): bash dsh-wsl-kit/scripts/link-linux-plugins.sh

Tool	Role
`vllm_status`	reachability + models
`vllm_chat`	chat completions

baseUrl / defaultModel / timeoutMs

Prefer Docker/AI1 history over Windows-native vLLM. Env: DSH_VLLM_BASE, DSH_VLLM_MODEL.

Field	Value
Plugin	`dsh-wsl-vllm` 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 `0.2.1-rc.5`) — single source of truth for the suite
Kit set	optional (not in `install.sh` / `KIT_SET=daily` by default)

MIT