cuda-remote-manager

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.