This project provides a Docker container setup for running Ollama with CUDA support on RunPod. It leverages the container templates and scripts from the RunPod Containers repository to ensure compatibility with the RunPod platform.
This is an unofficial, community-driven project and is not affiliated with RunPod or Ollama. While this container is designed to work on RunPod's infrastructure, it is independently maintained and not officially supported by RunPod. This project was created to support personal development work with AI agents and is shared with the community in hopes that others might find it useful.
The goal of this project is to create an easy-to-use, production-ready Docker container that:
- Runs Ollama with full CUDA support
- Is optimized for deployment on RunPod's GPU infrastructure
- Follows RunPod's container best practices and requirements
- Provides a seamless experience for running large language models
- CUDA support for GPU acceleration
- Integration with RunPod's infrastructure
- Optimized for AI/ML workloads
- Easy deployment and scaling
- Ollama - The core LLM serving framework
- RunPod - Cloud GPU platform
- RunPod Containers - Base container templates and scripts
[Documentation and setup instructions will be added as the project develops]
Contributions are welcome! Please feel free to submit a Pull Request.
[License information to be added]