vram-gpu-oom

GPU VRAM management patterns for sharing memory across services (Ollama, Whisper, ComfyUI). OOM retry logic, auto-unload on idle, and service signaling protocol.

$ Instalar

git clone https://github.com/lawless-m/claude-skills /tmp/claude-skills && cp -r /tmp/claude-skills/.claude/skills/Vram-GPU-OOM-memory-management ~/.claude/skills/claude-skills

// tip: Run this command in your terminal to install the skill