hwdsl2/docker-ollama
Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.
GitHub repository with 7 stars and 0 forks.
Language: Shell
Topics: ai, authentication, cuda, deep-learning, docker, docker-compose, docker-image, gpu, inference, langchain