Overview

​

Serverless

​

GPUs

• Generate images with SDXL Turbo: Learn how to build a web application using Runpod’s Serverless Workers and SDXL Turbo from Stability AI, a fast text-to-image model, and send requests to an Endpoint to generate images from text-based inputs.
• Run Google’s Gemma model: Deploy Google’s Gemma model on Runpod’s vLLM Worker, create a Serverless Endpoint, and interact with the model using OpenAI APIs and Python.
• Run your first serverless endpoint with Stable Diffusion: Use Runpod’s Stable Diffusion v1 inference endpoint to generate images, set up your serverless worker, start a job, check job status, and retrieve results.

​

CPUs

• Run an Ollama Server on a Runpod CPU: Set up and run an Ollama server on Runpod CPU for inference with this step-by-step tutorial.

​

Pods

​

GPUs

• Fine tune an LLM with Axolotl on Runpod: Learn how to fine-tune large language models with Axolotl on Runpod, a streamlined workflow for configuring and training AI models with GPU resources, and explore examples for LLaMA2, Gemma, LLaMA3, and Jamba.
• Run Fooocus in Jupyter Notebook: Learn how to run Fooocus, an open-source image generating model, in a Jupyter Notebook and launch the Gradio-based interface in under 5 minutes, with minimal requirements of 4GB Nvidia GPU memory and 8GB system memory.
• Build Docker Images on Runpod with Bazel: Learn how to build Docker images on Runpod using Bazel, a powerful build tool for creating consistent and efficient builds.
• Set up Ollama on your GPU Pod: Set up Ollama, a powerful language model, on a GPU Pod using Runpod, and interact with it through HTTP API requests, harnessing the power of GPU acceleration for your AI projects.
• Run your first Fast Stable Diffusion with Jupyter Notebook: Deploy a Jupyter Notebook to Runpod and generate your first image with Stable Diffusion in just 20 minutes, requiring Hugging Face user access token, RunPod infrastructure, and basic familiarity with the platform.

​

Containers

• Persist data outside of containers: Learn how to persist data outside of containers by creating named volumes, mounting volumes to data directories, and accessing persisted data from multiple container runs and removals in Docker.
• Containers overview: Discover the world of containerization with Docker, a platform for isolated environments that package applications, frameworks, and libraries into self-contained containers for consistent and reliable deployment across diverse computing environments.
• Dockerfile: Learn how to create a Dockerfile to customize a Docker image and use an entrypoint script to run a command when the container starts, making it a reusable and executable unit for deploying and sharing applications.
• Docker commands: Runpod enables BYOC development with Docker, providing a reference sheet for commonly used Docker commands, including login, images, containers, Dockerfile, volumes, network, and execute.

​

Integrations

​

OpenAI

• Overview: Use the OpenAI SDK to integrate with your Serverless Endpoints.

​

SkyPilot

• Running Runpod on SkyPilot: Learn how to deploy Pods from Runpod using SkyPilot.

​

Mods

• Running Runpod on Mods: Learn to integrate into Charm’s Mods tool chain and use Runpod as the Serverless Endpoint.

​

Migration

​

Cog

• Cog Migration: Migrate your Cog model from Replicate.com to Runpod by following this step-by-step guide, covering setup, model identification, Docker image building, and serverless endpoint creation.

​

Banana

• Banana migration: Quickly migrate from Banana to Runpod with Docker, leveraging a bridge between the two environments for a seamless transition. Utilize a Dockerfile to encapsulate your environment and deploy existing projects to Runpod with minimal adjustments.