We built a tool that installs frameworks like ComfyUI, Ollama, OpenWebUI etc on any cloud GPU in one command and saves your whole setup between sessions [R]

2026-05-19 · Source: Machine Learning · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure, Software Development & Engineering · Depth: Intermediate, quick

Summary

swm is an open-source command-line interface (CLI) tool designed to streamline the deployment and management of AI frameworks like ComfyUI, Ollama, and OpenWebUI on various cloud GPU providers. It addresses the common issue of repeatedly reinstalling software, custom nodes, models, and configurations when renting GPUs. The tool allows users to find the cheapest available GPUs across providers like RunPod, Vast.ai, and Lambda, spin up instances, and install frameworks with a single command. Its core feature is workspace synchronization, which saves an entire setup to S3-compatible object storage and restores it on any new instance, ensuring portability and persistence between sessions. Additionally, swm includes a lifecycle guard that automatically saves the workspace and terminates the GPU instance after 30 minutes of inactivity, preventing unexpected costs.

Key takeaway

For AI Engineers and MLOps teams frequently renting cloud GPUs for development or inference, swm offers a solution to eliminate repetitive setup and reduce idle costs. You should integrate swm into your workflow to automate framework installations, ensure your custom configurations and models persist across sessions, and leverage its lifecycle guard to prevent unnecessary billing from forgotten instances. This tool can significantly improve efficiency and cost-effectiveness.

Key insights

swm simplifies cloud GPU workflow by automating setup, syncing workspaces, and managing costs across providers.

Principles

• Automate repetitive setup tasks.
• Ensure workspace portability and persistence.
• Implement cost-saving automation.

Method

The swm method involves using CLI commands to find GPUs, create instances, install frameworks, and synchronize workspaces to S3-compatible storage for session persistence and cost management.

In practice

• Use `swm gpus` to compare GPU prices.
• Employ workspace sync for persistent setups.
• Configure the lifecycle guard to prevent idle charges.

Topics

• Cloud GPU Provisioning
• Workspace Synchronization
• ComfyUI
• Ollama
• OpenWebUI

Code references

• swm-gpu/swm

Best for: NLP Engineer, Computer Vision Engineer, Machine Learning Engineer, AI Engineer, MLOps Engineer

Related on AIssential

• GPU Clouds, Aggregators, and the New Economics of AI Compute — GPU cloud providers offer diverse services and pricing, necessitating careful evaluation based on security, managed services, and workload portability.
• INSTALL UNCENSORED TextGen Ai WebUI 2025 LOCALLY in 1 CLICK! — Running local AI models offers privacy, consistent performance, and uncensored content, with options for both local GPUs and cloud rentals.
• Under 5 minutes to a deployed LLM endpoint — Audry Hsu, RunPod — RunPod offers flexible, auto-scaling GPU infrastructure for rapid LLM deployment, abstracting away hardware management for developers.
• "But OpenClaw is expensive..." — A hybrid LLM architecture combining cloud frontier models with local open-source models significantly cuts costs and boosts privacy.
• Introducing workspaces for Lambda Cloud — Lambda Cloud "workspaces" provide logical containers for GPU resources, enhancing access control and environment separation.
• Snap’s GPU-Accelerated Secret to Processing 10 Petabytes a Day | NVIDIA AI Podcast Ep. 298 — Leveraging idle GPU capacity with NVIDIA Spark RAPIDS dramatically cuts data processing costs and resource consumption.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Machine Learning.