dsh-gpu

GPU-aware execution layer for DeepSeek Harness: gpu_status / gpu_exec / gpu_run_bg tools, per-step GPU context injection, automatic CUDA_VISIBLE_DEVICES card selection

AI Analysis

核心用途是让 DSH 能够感知和调度本地或远程 GPU 资源。适合需要在 Agent 任务中监控显存、自动选择空闲 CUDA 卡运行代码的开发者。

other

Package: dsh-gpu
Version: 0.1.4
License: MIT
Last updated: Aug 14, 2026

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zytsyj/dsh-gpu

README

Read the full README ↗

Configuration

- id: gpu
  name: dsh-gpu
  config:
    stepContext: true      # per-step GPU snapshot line (default true)
    refreshIntervalMs: 60000  # min spacing between injected snapshots
    queryTimeoutMs: 10000     # nvidia-smi timeout
    busyMemoryPct: 80         # >= this % memory used => busy
    busyUtilPct: 50           # >= this % SM util => busy