cuda-remote-manager

Manage remote CUDA machines with GPU monitoring and vLLM server control.

2|Updated Jan 30, 2026

Search Tags:#docker #gpu #ssh #cuda #vllm #remote development #llm inference

Ready to run

npx skills add https://github.com/amdmax/claude_marketplace --skill cuda-remote-manager

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: cuda-remote-manager
Source: https://github.com/amdmax/claude_marketplace/tree/main/.claude/skills/cuda-remote-manager
Command: npx skills add https://github.com/amdmax/claude_marketplace --skill cuda-remote-manager

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the management of a remote CUDA development machine, enabling efficient use of its powerful GPU for deep learning inference and CUDA programming.

Core Features & Use Cases

Remote Access & Status: Connect to, check the status of, and manage the power of the remote machine.
AI Model Serving: Start, stop, and monitor vLLM inference servers for large language models.
Development Environment: Compile and run CUDA programs, and configure VS Code for remote development.
Use Case: You need to run a large language model for code generation on your powerful remote GPU server. This Skill allows you to easily start the vLLM server, check GPU utilization, and connect your local VS Code to the remote machine for development.

Quick Start

Use the cuda-remote-manager skill to start a vLLM server with the Qwen2.5-Coder-7B model on the remote machine.

Frequently Asked Questions about cuda-remote-manager

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I manage a remote CUDA development machine for deep learning inference?▼

To manage a remote CUDA development machine for deep learning inference, you can use remote SSH to connect, check system status, monitor GPU utilization, and compile or execute CUDA programs directly on the server.

How do I start a vLLM server on a remote GPU for large language model inference?▼

Starting a vLLM server on a remote GPU involves establishing an SSH connection to the machine, then issuing commands to launch and monitor the vLLM inference server process for your target large language model.

Can I configure VS Code remote SSH for CUDA programming on an external GPU server?▼

Yes, you can configure VS Code remote SSH to connect to an external GPU server, allowing you to compile and run CUDA programs from your local development environment while utilizing the remote hardware.

Do I need Docker to run vLLM and LiteLLM proxy on a remote CUDA machine?▼

Using Docker for vLLM and LiteLLM proxy on a remote CUDA machine streamlines environment management, allowing you to deploy AI coding assistants and manage large language model inference without modifying the host system.

What is the best way to monitor GPU utilization on an RTX 5090 during LLM inference?▼

Monitoring GPU utilization on an RTX 5090 during LLM inference requires establishing a remote SSH connection and running system status checks to observe real-time power consumption and compute metrics.

How do I set up a LiteLLM proxy for an AI coding assistant using a remote GPU?▼

Setting up a LiteLLM proxy for an AI coding assistant on a remote GPU requires connecting via SSH, configuring the proxy to route requests, and starting the vLLM inference server to handle the large language model workload.