Vram-GPU-OOM

Name: Vram-GPU-OOM
Availability: InStock
Author: lawless-m

Community

Smart GPU VRAM sharing across services.

Software Engineering #gpu #retry #multiservice #vrAM #oom

Authorlawless-m

Version1.0.0

Installs0

System Documentation

What problem does it solve?

This Skill provides GPU VRAM sharing and OOM retry patterns to coordinate memory across Ollama, Whisper, and ComfyUI, with auto-unload and signaling endpoints.

Core Features & Use Cases

Cross-service OOM retry with delays
Auto-unload on idle to free VRAM
Optional signaling endpoints to request unloads

Quick Start

Implement OOM retry logic and configure auto-unload; test with smaller models before scaling up.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: Vram-GPU-OOM
Download link: https://github.com/lawless-m/Gwen/archive/main.zip#vram-gpu-oom

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.

View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.